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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - selftests improvements
   - large PUD support for HugeTLB
   - single-stepping fixes
   - improved tracing
   - various timer and vGIC fixes

  x86:
   - Processor Tracing virtualization
   - STIBP support
   - some correctness fixes
   - refactorings and splitting of vmx.c
   - use the Hyper-V range TLB flush hypercall
   - reduce order of vcpu struct
   - WBNOINVD support
   - do not use -ftrace for __noclone functions
   - nested guest support for PAUSE filtering on AMD
   - more Hyper-V enlightenments (direct mode for synthetic timers)

  PPC:
   -  nested VFIO

  s390:
   - bugfixes only this time"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits)
  KVM: x86: Add CPUID support for new instruction WBNOINVD
  kvm: selftests: ucall: fix exit mmio address guessing
  Revert "compiler-gcc: disable -ftracer for __noclone functions"
  KVM: VMX: Move VM-Enter + VM-Exit handling to non-inline sub-routines
  KVM: VMX: Explicitly reference RCX as the vmx_vcpu pointer in asm blobs
  KVM: x86: Use jmp to invoke kvm_spurious_fault() from .fixup
  MAINTAINERS: Add arch/x86/kvm sub-directories to existing KVM/x86 entry
  KVM/x86: Use SVM assembly instruction mnemonics instead of .byte streams
  KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()
  KVM/MMU: Flush tlb directly in kvm_set_pte_rmapp()
  KVM/MMU: Move tlb flush in kvm_set_pte_rmapp() to kvm_mmu_notifier_change_pte()
  KVM: Make kvm_set_spte_hva() return int
  KVM: Replace old tlb flush function with new one to flush a specified range.
  KVM/MMU: Add tlb flush with range helper function
  KVM/VMX: Add hv tlb range flush support
  x86/hyper-v: Add HvFlushGuestAddressList hypercall support
  KVM: Add tlb_remote_flush_with_range callback in kvm_x86_ops
  KVM: x86: Disable Intel PT when VMXON in L1 guest
  KVM: x86: Set intercept for Intel PT MSRs read/write
  KVM: x86: Implement Intel PT MSRs read/write emulation
  ...

18 files changed, 387 insertions, 100 deletions

diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index d9a725478375..72c25a3cb658 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -6,7 +6,7 @@ TEST_PROGS := run.sh
 
 include ../lib.mk
 
-all: khdr
+all:
 	@for DIR in $(SUBDIRS); do		\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
 		mkdir $$BUILD_TARGET  -p;	\
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index ad1eeb14fda7..30996306cabc 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -19,6 +19,7 @@ TEST_GEN_FILES := \
 TEST_PROGS := run.sh
 
 top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
 include ../../lib.mk
 
 $(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 46648427d537..07f572a1bd3f 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -10,8 +10,6 @@ TEST_PROGS_EXTENDED := gpio-mockup-chardev
 GPIODIR := $(realpath ../../../gpio)
 GPIOOBJ := gpio-utils.o
 
-include ../lib.mk
-
 all: $(TEST_PROGS_EXTENDED)
 
 override define CLEAN
@@ -19,7 +17,9 @@ override define CLEAN
 	$(MAKE) -C $(GPIODIR) OUTPUT=$(GPIODIR)/ clean
 endef
 
-$(TEST_PROGS_EXTENDED):| khdr
+KSFT_KHDR_INSTALL := 1
+include ../lib.mk
+
 $(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
 
 $(GPIODIR)/$(GPIOOBJ):
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 01a219229238..f9a0e9938480 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,6 +1,7 @@
 all:
 
 top_srcdir = ../../../..
+KSFT_KHDR_INSTALL := 1
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
@@ -14,9 +15,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 
 TEST_GEN_PROGS_aarch64 += dirty_log_test
+TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
@@ -44,7 +48,6 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 
 all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
-$(STATIC_LIBS):| khdr
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
 cscope:
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
new file mode 100644
index 000000000000..749336937d37
--- /dev/null
+++ b/tools/testing/selftests/kvm/clear_dirty_log_test.c
@@ -0,0 +1,2 @@
+#define USE_CLEAR_DIRTY_LOG
+#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index aeff95a91b15..4715cfba20dc 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -51,10 +51,17 @@ static uint64_t random_array[TEST_PAGES_PER_LOOP];
 static uint64_t iteration;
 
 /*
- * GPA offset of the testing memory slot. Must be bigger than
- * DEFAULT_GUEST_PHY_PAGES.
+ * 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_mem = DEFAULT_GUEST_TEST_MEM;
+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;
 
 /*
  * Continuously write to the first 8 bytes of a random pages within
@@ -66,7 +73,7 @@ static void guest_code(void)
 
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			uint64_t addr = guest_test_mem;
+			uint64_t addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
 			addr &= ~(host_page_size - 1);
@@ -209,12 +216,14 @@ static void vm_dirty_log_verify(unsigned long *bmap)
 }
 
 static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
-				uint64_t extra_mem_pages, void *guest_code)
+				uint64_t extra_mem_pages, void *guest_code,
+				unsigned long type)
 {
 	struct kvm_vm *vm;
 	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
-	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, type);
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 #ifdef __x86_64__
 	vm_create_irqchip(vm);
@@ -224,13 +233,14 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 }
 
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     unsigned long interval, bool top_offset)
+		     unsigned long interval, uint64_t phys_offset)
 {
 	unsigned int guest_pa_bits, guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
 	uint64_t max_gfn;
 	unsigned long *bmap;
+	unsigned long type = 0;
 
 	switch (mode) {
 	case VM_MODE_P52V48_4K:
@@ -241,6 +251,14 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		guest_pa_bits = 52;
 		guest_page_shift = 16;
 		break;
+	case VM_MODE_P48V48_4K:
+		guest_pa_bits = 48;
+		guest_page_shift = 12;
+		break;
+	case VM_MODE_P48V48_64K:
+		guest_pa_bits = 48;
+		guest_page_shift = 16;
+		break;
 	case VM_MODE_P40V48_4K:
 		guest_pa_bits = 40;
 		guest_page_shift = 12;
@@ -255,6 +273,19 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
+#ifdef __x86_64__
+	/*
+	 * FIXME
+	 * The x86_64 kvm selftests framework currently only supports a
+	 * single PML4 which restricts the number of physical address
+	 * bits we can change to 39.
+	 */
+	guest_pa_bits = 39;
+#endif
+#ifdef __aarch64__
+	if (guest_pa_bits != 40)
+		type = KVM_VM_TYPE_ARM_IPA_SIZE(guest_pa_bits);
+#endif
 	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
 	guest_page_size = (1ul << guest_page_shift);
 	/* 1G of guest page sized pages */
@@ -263,31 +294,41 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
-	if (top_offset) {
-		guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
-		guest_test_mem &= ~(host_page_size - 1);
+	if (!phys_offset) {
+		guest_test_phys_mem = (max_gfn - guest_num_pages) * guest_page_size;
+		guest_test_phys_mem &= ~(host_page_size - 1);
+	} else {
+		guest_test_phys_mem = phys_offset;
 	}
 
-	DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
+	DEBUG("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
 
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-	vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
+	vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code, type);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	struct kvm_enable_cap cap = {};
+
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT;
+	cap.args[0] = 1;
+	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_mem,
+				    guest_test_phys_mem,
 				    TEST_MEM_SLOT_INDEX,
 				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
 
-	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, guest_test_mem, guest_test_mem,
+	/* Do mapping for the dirty track memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem,
 		 guest_num_pages * guest_page_size, 0);
 
 	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
 
 #ifdef __x86_64__
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -299,7 +340,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	/* 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, guest_test_mem);
+	sync_global_to_guest(vm, guest_test_virt_mem);
 	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
@@ -316,6 +357,10 @@ static void run_test(enum vm_guest_mode mode, unsigned long 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,
+				       DIV_ROUND_UP(host_num_pages, 64) * 64);
+#endif
 		vm_dirty_log_verify(bmap);
 		iteration++;
 		sync_global_to_guest(vm, iteration);
@@ -335,23 +380,16 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	kvm_vm_free(vm);
 }
 
-static struct vm_guest_modes {
-	enum vm_guest_mode mode;
+struct vm_guest_mode_params {
 	bool supported;
 	bool enabled;
-} vm_guest_modes[NUM_VM_MODES] = {
-#if defined(__x86_64__)
-	{ VM_MODE_P52V48_4K,	1, 1, },
-	{ VM_MODE_P52V48_64K,	0, 0, },
-	{ VM_MODE_P40V48_4K,	0, 0, },
-	{ VM_MODE_P40V48_64K,	0, 0, },
-#elif defined(__aarch64__)
-	{ VM_MODE_P52V48_4K,	0, 0, },
-	{ VM_MODE_P52V48_64K,	0, 0, },
-	{ VM_MODE_P40V48_4K,	1, 1, },
-	{ VM_MODE_P40V48_64K,	1, 1, },
-#endif
 };
+struct vm_guest_mode_params vm_guest_mode_params[NUM_VM_MODES];
+
+#define vm_guest_mode_params_init(mode, supported, enabled)					\
+({												\
+	vm_guest_mode_params[mode] = (struct vm_guest_mode_params){ supported, enabled };	\
+})
 
 static void help(char *name)
 {
@@ -359,25 +397,21 @@ static void help(char *name)
 
 	puts("");
 	printf("usage: %s [-h] [-i iterations] [-I interval] "
-	       "[-o offset] [-t] [-m mode]\n", name);
+	       "[-p offset] [-m mode]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
 	       TEST_HOST_LOOP_INTERVAL);
-	printf(" -o: guest test memory offset (default: 0x%lx)\n",
-	       DEFAULT_GUEST_TEST_MEM);
-	printf(" -t: map guest test memory at the top of the allowed "
-	       "physical address range\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",
-		       vm_guest_modes[i].mode,
-		       vm_guest_mode_string(vm_guest_modes[i].mode),
-		       vm_guest_modes[i].supported ? " (supported)" : "");
+		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
+		       vm_guest_mode_params[i].supported ? " (supported)" : "");
 	}
 	puts("");
 	exit(0);
@@ -388,11 +422,34 @@ int main(int argc, char *argv[])
 	unsigned long iterations = TEST_HOST_LOOP_N;
 	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
 	bool mode_selected = false;
-	bool top_offset = false;
-	unsigned int mode;
+	uint64_t phys_offset = 0;
+	unsigned int mode, host_ipa_limit;
 	int opt, i;
 
-	while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
+#ifdef USE_CLEAR_DIRTY_LOG
+	if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT)) {
+		fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n");
+		exit(KSFT_SKIP);
+	}
+#endif
+
+#ifdef __x86_64__
+	vm_guest_mode_params_init(VM_MODE_P52V48_4K, true, true);
+#endif
+#ifdef __aarch64__
+	vm_guest_mode_params_init(VM_MODE_P40V48_4K, true, true);
+	vm_guest_mode_params_init(VM_MODE_P40V48_64K, true, true);
+
+	host_ipa_limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+	if (host_ipa_limit >= 52)
+		vm_guest_mode_params_init(VM_MODE_P52V48_64K, true, true);
+	if (host_ipa_limit >= 48) {
+		vm_guest_mode_params_init(VM_MODE_P48V48_4K, true, true);
+		vm_guest_mode_params_init(VM_MODE_P48V48_64K, true, true);
+	}
+#endif
+
+	while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -400,22 +457,19 @@ int main(int argc, char *argv[])
 		case 'I':
 			interval = strtol(optarg, NULL, 10);
 			break;
-		case 'o':
-			guest_test_mem = strtoull(optarg, NULL, 0);
-			break;
-		case 't':
-			top_offset = true;
+		case 'p':
+			phys_offset = strtoull(optarg, NULL, 0);
 			break;
 		case 'm':
 			if (!mode_selected) {
 				for (i = 0; i < NUM_VM_MODES; ++i)
-					vm_guest_modes[i].enabled = 0;
+					vm_guest_mode_params[i].enabled = false;
 				mode_selected = true;
 			}
 			mode = strtoul(optarg, NULL, 10);
 			TEST_ASSERT(mode < NUM_VM_MODES,
 				    "Guest mode ID %d too big", mode);
-			vm_guest_modes[mode].enabled = 1;
+			vm_guest_mode_params[mode].enabled = true;
 			break;
 		case 'h':
 		default:
@@ -426,8 +480,6 @@ int main(int argc, char *argv[])
 
 	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
 	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
-	TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
-		    "Cannot use both -o [offset] and -t at the same time");
 
 	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
 	      iterations, interval);
@@ -435,13 +487,12 @@ int main(int argc, char *argv[])
 	srandom(time(0));
 
 	for (i = 0; i < NUM_VM_MODES; ++i) {
-		if (!vm_guest_modes[i].enabled)
+		if (!vm_guest_mode_params[i].enabled)
 			continue;
-		TEST_ASSERT(vm_guest_modes[i].supported,
+		TEST_ASSERT(vm_guest_mode_params[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
-			    vm_guest_modes[i].mode,
-			    vm_guest_mode_string(vm_guest_modes[i].mode));
-		run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
+			    i, vm_guest_mode_string(i));
+		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 a4e59e3b4826..a84785b02557 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -36,6 +36,8 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 enum vm_guest_mode {
 	VM_MODE_P52V48_4K,
 	VM_MODE_P52V48_64K,
+	VM_MODE_P48V48_4K,
+	VM_MODE_P48V48_64K,
 	VM_MODE_P40V48_4K,
 	VM_MODE_P40V48_64K,
 	NUM_VM_MODES,
@@ -54,10 +56,14 @@ int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
 
 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, unsigned long type);
 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);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+			    uint64_t first_page, uint32_t num_pages);
 
 int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
 		       size_t len);
@@ -78,6 +84,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 
 void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 		void *arg);
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b6022e2f116e..e8c42506a09d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -268,13 +268,20 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
 
 	switch (vm->mode) {
 	case VM_MODE_P52V48_4K:
-		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
-		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
-		break;
+		TEST_ASSERT(false, "AArch64 does not support 4K sized pages "
+				   "with 52-bit physical address ranges");
 	case VM_MODE_P52V48_64K:
 		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
 		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
 		break;
+	case VM_MODE_P48V48_4K:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+		break;
+	case VM_MODE_P48V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+		break;
 	case VM_MODE_P40V48_4K:
 		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
 		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
@@ -305,7 +312,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
 	get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
 
-        fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
-                indent, "", pstate, pc);
-
+	fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+		indent, "", pstate, pc);
 }
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1b41e71283d5..23022e9d32eb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -85,13 +85,13 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
 	return ret;
 }
 
-static void vm_open(struct kvm_vm *vm, int perm)
+static void vm_open(struct kvm_vm *vm, int perm, unsigned long type)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
 	if (vm->kvm_fd < 0)
 		exit(KSFT_SKIP);
 
-	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL);
+	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
 	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
 		"rc: %i errno: %i", vm->fd, errno);
 }
@@ -99,9 +99,13 @@ static void vm_open(struct kvm_vm *vm, int perm)
 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",
 };
+_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
+	       "Missing new mode strings?");
 
 /*
  * VM Create
@@ -122,7 +126,8 @@ const char * const vm_guest_mode_string[] = {
  * 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, unsigned long type)
 {
 	struct kvm_vm *vm;
 	int kvm_fd;
@@ -131,22 +136,38 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
 	vm->mode = mode;
-	vm_open(vm, perm);
+	vm->type = type;
+	vm_open(vm, perm, type);
 
 	/* Setup mode specific traits. */
 	switch (vm->mode) {
 	case VM_MODE_P52V48_4K:
 		vm->pgtable_levels = 4;
+		vm->pa_bits = 52;
+		vm->va_bits = 48;
 		vm->page_size = 0x1000;
 		vm->page_shift = 12;
-		vm->va_bits = 48;
 		break;
 	case VM_MODE_P52V48_64K:
 		vm->pgtable_levels = 3;
 		vm->pa_bits = 52;
+		vm->va_bits = 48;
 		vm->page_size = 0x10000;
 		vm->page_shift = 16;
+		break;
+	case VM_MODE_P48V48_4K:
+		vm->pgtable_levels = 4;
+		vm->pa_bits = 48;
+		vm->va_bits = 48;
+		vm->page_size = 0x1000;
+		vm->page_shift = 12;
+		break;
+	case VM_MODE_P48V48_64K:
+		vm->pgtable_levels = 3;
+		vm->pa_bits = 48;
 		vm->va_bits = 48;
+		vm->page_size = 0x10000;
+		vm->page_shift = 16;
 		break;
 	case VM_MODE_P40V48_4K:
 		vm->pgtable_levels = 4;
@@ -186,6 +207,11 @@ 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, 0);
+}
+
 /*
  * VM Restart
  *
@@ -203,7 +229,7 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
 {
 	struct userspace_mem_region *region;
 
-	vm_open(vmp, perm);
+	vm_open(vmp, perm, vmp->type);
 	if (vmp->has_irqchip)
 		vm_create_irqchip(vmp);
 
@@ -231,6 +257,19 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
 		    strerror(-ret));
 }
 
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+			    uint64_t first_page, uint32_t num_pages)
+{
+	struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
+		                            .first_page = first_page,
+	                                    .num_pages = num_pages };
+	int ret;
+
+	ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
+	TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s",
+		    strerror(-ret));
+}
+
 /*
  * Userspace Memory Region Find
  *
@@ -1270,14 +1309,24 @@ int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
 		unsigned long cmd, void *arg)
 {
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, cmd, arg);
+	TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
+		cmd, ret, errno, strerror(errno));
+}
+
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
+		unsigned long cmd, void *arg)
+{
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int ret;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 
 	ret = ioctl(vcpu->fd, cmd, arg);
-	TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
-		cmd, ret, errno, strerror(errno));
+
+	return ret;
 }
 
 /*
@@ -1422,7 +1471,7 @@ const char *exit_reason_str(unsigned int exit_reason)
  *
  * Within the VM specified by vm, locates a range of available physical
  * pages at or above paddr_min. If found, the pages are marked as in use
- * and thier base address is returned. A TEST_ASSERT failure occurs if
+ * and their base address is returned. A TEST_ASSERT failure occurs if
  * not enough pages are available at or above paddr_min.
  */
 vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 52701db0f253..4595e42c6e29 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -44,6 +44,7 @@ struct vcpu {
 
 struct kvm_vm {
 	int mode;
+	unsigned long type;
 	int kvm_fd;
 	int fd;
 	unsigned int pgtable_levels;
diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c
index 4777f9bb5194..a2ab38be2f47 100644
--- a/tools/testing/selftests/kvm/lib/ucall.c
+++ b/tools/testing/selftests/kvm/lib/ucall.c
@@ -34,7 +34,8 @@ void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
 		return;
 
 	if (type == UCALL_MMIO) {
-		vm_paddr_t gpa, start, end, step;
+		vm_paddr_t gpa, start, end, step, offset;
+		unsigned bits;
 		bool ret;
 
 		if (arg) {
@@ -45,25 +46,30 @@ void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
 		}
 
 		/*
-		 * Find an address within the allowed virtual address space,
-		 * that does _not_ have a KVM memory region associated with it.
-		 * Identity mapping an address like this allows the guest to
+		 * Find an address within the allowed physical and virtual address
+		 * spaces, that does _not_ have a KVM memory region associated with
+		 * it. Identity mapping an address like this allows the guest to
 		 * access it, but as KVM doesn't know what to do with it, it
 		 * will assume it's something userspace handles and exit with
 		 * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
-		 * Here we start with a guess that the addresses around two
-		 * thirds of the VA space are unmapped and then work both down
-		 * and up from there in 1/6 VA space sized steps.
+		 * Here we start with a guess that the addresses around 5/8th
+		 * of the allowed space are unmapped and then work both down and
+		 * up from there in 1/16th allowed space sized steps.
+		 *
+		 * Note, we need to use VA-bits - 1 when calculating the allowed
+		 * virtual address space for an identity mapping because the upper
+		 * half of the virtual address space is the two's complement of the
+		 * lower and won't match physical addresses.
 		 */
-		start = 1ul << (vm->va_bits * 2 / 3);
-		end = 1ul << vm->va_bits;
-		step = 1ul << (vm->va_bits / 6);
-		for (gpa = start; gpa >= 0; gpa -= step) {
-			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+		bits = vm->va_bits - 1;
+		bits = vm->pa_bits < bits ? vm->pa_bits : bits;
+		end = 1ul << bits;
+		start = end * 5 / 8;
+		step = end / 16;
+		for (offset = 0; offset < end - start; offset += step) {
+			if (ucall_mmio_init(vm, start - offset))
 				return;
-		}
-		for (gpa = start + step; gpa < end; gpa += step) {
-			if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+			if (ucall_mmio_init(vm, start + offset))
 				return;
 		}
 		TEST_ASSERT(false, "Can't find a ucall mmio address");
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 92c2cfd1b182..ea3c73e8f4f6 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -113,8 +113,8 @@ int main(int argc, char *argv[])
 	for (stage = 1;; stage++) {
 		_vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
-			    run->exit_reason,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
 		memset(&regs1, 0, sizeof(regs1));
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
new file mode 100644
index 000000000000..264425f75806
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_CAP_HYPERV_CPUID
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+static void guest_code(void)
+{
+}
+
+static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
+			  int evmcs_enabled)
+{
+	int i;
+
+	if (!evmcs_enabled)
+		TEST_ASSERT(hv_cpuid_entries->nent == 6,
+			    "KVM_GET_SUPPORTED_HV_CPUID should return 6 entries"
+			    " when Enlightened VMCS is disabled (returned %d)",
+			    hv_cpuid_entries->nent);
+	else
+		TEST_ASSERT(hv_cpuid_entries->nent == 7,
+			    "KVM_GET_SUPPORTED_HV_CPUID should return 7 entries"
+			    " when Enlightened VMCS is enabled (returned %d)",
+			    hv_cpuid_entries->nent);
+
+	for (i = 0; i < hv_cpuid_entries->nent; i++) {
+		struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
+
+		TEST_ASSERT((entry->function >= 0x40000000) &&
+			    (entry->function <= 0x4000000A),
+			    "function %lx is our of supported range",
+			    entry->function);
+
+		TEST_ASSERT(entry->index == 0,
+			    ".index field should be zero");
+
+		TEST_ASSERT(entry->index == 0,
+			    ".index field should be zero");
+
+		TEST_ASSERT(entry->flags == 0,
+			    ".flags field should be zero");
+
+		TEST_ASSERT(entry->padding[0] == entry->padding[1]
+			    == entry->padding[2] == 0,
+			    ".index field should be zero");
+
+		/*
+		 * If needed for debug:
+		 * fprintf(stdout,
+		 *	"CPUID%lx EAX=0x%lx EBX=0x%lx ECX=0x%lx EDX=0x%lx\n",
+		 *	entry->function, entry->eax, entry->ebx, entry->ecx,
+		 *	entry->edx);
+		 */
+	}
+
+}
+
+void test_hv_cpuid_e2big(struct kvm_vm *vm)
+{
+	static struct kvm_cpuid2 cpuid = {.nent = 0};
+	int ret;
+
+	ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+
+	TEST_ASSERT(ret == -1 && errno == E2BIG,
+		    "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
+		    " it should have: %d %d", ret, errno);
+}
+
+
+struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
+{
+	int nent = 20; /* should be enough */
+	static struct kvm_cpuid2 *cpuid;
+	int ret;
+
+	cpuid = malloc(sizeof(*cpuid) + nent * sizeof(struct kvm_cpuid_entry2));
+
+	if (!cpuid) {
+		perror("malloc");
+		abort();
+	}
+
+	cpuid->nent = nent;
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+
+	return cpuid;
+}
+
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	int rv;
+	uint16_t evmcs_ver;
+	struct kvm_cpuid2 *hv_cpuid_entries;
+	struct kvm_enable_cap enable_evmcs_cap = {
+		.cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+		 .args[0] = (unsigned long)&evmcs_ver
+	};
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
+	if (!rv) {
+		fprintf(stderr,
+			"KVM_CAP_HYPERV_CPUID not supported, skip test\n");
+		exit(KSFT_SKIP);
+	}
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	test_hv_cpuid_e2big(vm);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+	if (!hv_cpuid_entries)
+		return 1;
+
+	test_hv_cpuid(hv_cpuid_entries, 0);
+
+	free(hv_cpuid_entries);
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+	if (!hv_cpuid_entries)
+		return 1;
+
+	test_hv_cpuid(hv_cpuid_entries, 1);
+
+	free(hv_cpuid_entries);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 03da41f0f736..4b3f556265f1 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -152,8 +152,8 @@ int main(int argc, char *argv[])
 	for (stage = 1;; stage++) {
 		_vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
-			    "Unexpected exit reason: %u (%s),\n",
-			    run->exit_reason,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
 		memset(&regs1, 0, sizeof(regs1));
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 0a8e75886224..8b0f16409ed7 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -16,18 +16,18 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
 TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
 TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
 
+ifdef KSFT_KHDR_INSTALL
 top_srcdir ?= ../../../..
 include $(top_srcdir)/scripts/subarch.include
 ARCH		?= $(SUBARCH)
 
-all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
-
 .PHONY: khdr
 khdr:
 	make ARCH=$(ARCH) -C $(top_srcdir) headers_install
 
-ifdef KSFT_KHDR_INSTALL
-$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr
+all: khdr $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+else
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 endif
 
 .ONESHELL:
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
index 14cfcf006936..c46c0eefab9e 100644
--- a/tools/testing/selftests/networking/timestamping/Makefile
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -6,6 +6,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp
 all: $(TEST_PROGS)
 
 top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile
index dc92eb271d9a..be5a5e542804 100644
--- a/tools/testing/selftests/tc-testing/bpf/Makefile
+++ b/tools/testing/selftests/tc-testing/bpf/Makefile
@@ -4,6 +4,7 @@ APIDIR := ../../../../include/uapi
 TEST_GEN_FILES = action.o
 
 top_srcdir = ../../../../..
+KSFT_KHDR_INSTALL := 1
 include ../../lib.mk
 
 CLANG ?= clang
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 6e67e726e5a5..e13eb6cc8901 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -25,6 +25,7 @@ TEST_GEN_FILES += virtual_address_range
 
 TEST_PROGS := run_vmtests
 
+KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
 $(OUTPUT)/userfaultfd: LDLIBS += -lpthread