Merge branch 'kvm-sev-cgroup' into HEAD

3 files changed, 569 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
new file mode 100644
index 000000000000..cb953df4d7d0
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_GET_MSR_INDEX_LIST and
+ * KVM_GET_MSR_FEATURE_INDEX_LIST work as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#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"
+
+static int kvm_num_index_msrs(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+	TEST_ASSERT(r == -1 && errno == E2BIG,
+				"Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+				r);
+
+	r = list->nmsrs;
+	free(list);
+	return r;
+}
+
+static void test_get_msr_index(void)
+{
+	int old_res, res, kvm_fd, r;
+	struct kvm_msr_list *list;
+
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	old_res = kvm_num_index_msrs(kvm_fd, 0);
+	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+	if (old_res != 1) {
+		res = kvm_num_index_msrs(kvm_fd, 1);
+		TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+		TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+	}
+
+	list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0]));
+	list->nmsrs = old_res;
+	r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+
+	TEST_ASSERT(r == 0,
+		    "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+		    r);
+	TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical");
+	free(list);
+
+	close(kvm_fd);
+}
+
+static int kvm_num_feature_msrs(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+	TEST_ASSERT(r == -1 && errno == E2BIG,
+		"Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i",
+				r);
+
+	r = list->nmsrs;
+	free(list);
+	return r;
+}
+
+struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs)
+{
+	struct kvm_msr_list *list;
+	int r;
+
+	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+	list->nmsrs = nmsrs;
+	r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+
+	TEST_ASSERT(r == 0,
+		"Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+		r);
+
+	return list;
+}
+
+static void test_get_msr_feature(void)
+{
+	int res, old_res, i, kvm_fd;
+	struct kvm_msr_list *feature_list;
+
+	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+	if (kvm_fd < 0)
+		exit(KSFT_SKIP);
+
+	old_res = kvm_num_feature_msrs(kvm_fd, 0);
+	TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+	if (old_res != 1) {
+		res = kvm_num_feature_msrs(kvm_fd, 1);
+		TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+		TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+	}
+
+	feature_list = kvm_get_msr_feature_list(kvm_fd, old_res);
+	TEST_ASSERT(old_res == feature_list->nmsrs,
+				"Unmatching number of msr indexes");
+
+	for (i = 0; i < feature_list->nmsrs; i++)
+		kvm_get_feature_msr(feature_list->indices[i]);
+
+	free(feature_list);
+	close(kvm_fd);
+}
+
+int main(int argc, char *argv[])
+{
+	if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES))
+		test_get_msr_feature();
+
+	test_get_msr_index();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
new file mode 100644
index 000000000000..7f1d2765572c
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Tests for Hyper-V clocksources
+ */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+struct ms_hyperv_tsc_page {
+	volatile u32 tsc_sequence;
+	u32 reserved1;
+	volatile u64 tsc_scale;
+	volatile s64 tsc_offset;
+} __packed;
+
+#define HV_X64_MSR_GUEST_OS_ID			0x40000000
+#define HV_X64_MSR_TIME_REF_COUNT		0x40000020
+#define HV_X64_MSR_REFERENCE_TSC		0x40000021
+#define HV_X64_MSR_TSC_FREQUENCY		0x40000022
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
+#define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
+
+/* Simplified mul_u64_u64_shr() */
+static inline u64 mul_u64_u64_shr64(u64 a, u64 b)
+{
+	union {
+		u64 ll;
+		struct {
+			u32 low, high;
+		} l;
+	} rm, rn, rh, a0, b0;
+	u64 c;
+
+	a0.ll = a;
+	b0.ll = b;
+
+	rm.ll = (u64)a0.l.low * b0.l.high;
+	rn.ll = (u64)a0.l.high * b0.l.low;
+	rh.ll = (u64)a0.l.high * b0.l.high;
+
+	rh.l.low = c = rm.l.high + rn.l.high + rh.l.low;
+	rh.l.high = (c >> 32) + rh.l.high;
+
+	return rh.ll;
+}
+
+static inline void nop_loop(void)
+{
+	int i;
+
+	for (i = 0; i < 1000000; i++)
+		asm volatile("nop");
+}
+
+static inline void check_tsc_msr_rdtsc(void)
+{
+	u64 tsc_freq, r1, r2, t1, t2;
+	s64 delta_ns;
+
+	tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
+	GUEST_ASSERT(tsc_freq > 0);
+
+	/* First, check MSR-based clocksource */
+	r1 = rdtsc();
+	t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	nop_loop();
+	r2 = rdtsc();
+	t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+	GUEST_ASSERT(r2 > r1 && t2 > t1);
+
+	/* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+	delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+	if (delta_ns < 0)
+		delta_ns = -delta_ns;
+
+	/* 1% tolerance */
+	GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
+}
+
+static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page)
+{
+	return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+}
+
+static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
+{
+	u64 r1, r2, t1, t2;
+
+	/* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
+	t1 = get_tscpage_ts(tsc_page);
+	r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+	/* 10 ms tolerance */
+	GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
+	nop_loop();
+
+	t2 = get_tscpage_ts(tsc_page);
+	r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
+}
+
+static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa)
+{
+	u64 tsc_scale, tsc_offset;
+
+	/* Set Guest OS id to enable Hyper-V emulation */
+	GUEST_SYNC(1);
+	wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+	GUEST_SYNC(2);
+
+	check_tsc_msr_rdtsc();
+
+	GUEST_SYNC(3);
+
+	/* Set up TSC page is disabled state, check that it's clean */
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa);
+	GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+	GUEST_ASSERT(tsc_page->tsc_scale == 0);
+	GUEST_ASSERT(tsc_page->tsc_offset == 0);
+
+	GUEST_SYNC(4);
+
+	/* Set up TSC page is enabled state */
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa | 0x1);
+	GUEST_ASSERT(tsc_page->tsc_sequence != 0);
+
+	GUEST_SYNC(5);
+
+	check_tsc_msr_tsc_page(tsc_page);
+
+	GUEST_SYNC(6);
+
+	tsc_offset = tsc_page->tsc_offset;
+	/* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+
+	GUEST_SYNC(7);
+	/* Sanity check TSC page timestamp, it should be close to 0 */
+	GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000);
+
+	GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
+
+	nop_loop();
+
+	/*
+	 * Enable Re-enlightenment and check that TSC page stays constant across
+	 * KVM_SET_CLOCK.
+	 */
+	wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0x1 << 16 | 0xff);
+	wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0x1);
+	tsc_offset = tsc_page->tsc_offset;
+	tsc_scale = tsc_page->tsc_scale;
+	GUEST_SYNC(8);
+	GUEST_ASSERT(tsc_page->tsc_offset == tsc_offset);
+	GUEST_ASSERT(tsc_page->tsc_scale == tsc_scale);
+
+	GUEST_SYNC(9);
+
+	check_tsc_msr_tsc_page(tsc_page);
+
+	/*
+	 * Disable re-enlightenment and TSC page, check that KVM doesn't update
+	 * it anymore.
+	 */
+	wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0);
+	wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0);
+	wrmsr(HV_X64_MSR_REFERENCE_TSC, 0);
+	memset(tsc_page, 0, sizeof(*tsc_page));
+
+	GUEST_SYNC(10);
+	GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+	GUEST_ASSERT(tsc_page->tsc_offset == 0);
+	GUEST_ASSERT(tsc_page->tsc_scale == 0);
+
+	GUEST_DONE();
+}
+
+#define VCPU_ID 0
+
+static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
+{
+	u64 tsc_freq, r1, r2, t1, t2;
+	s64 delta_ns;
+
+	tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
+	TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
+
+	/* First, check MSR-based clocksource */
+	r1 = rdtsc();
+	t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	nop_loop();
+	r2 = rdtsc();
+	t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+
+	TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
+
+	/* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+	delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+	if (delta_ns < 0)
+		delta_ns = -delta_ns;
+
+	/* 1% tolerance */
+	TEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100,
+		    "Elapsed time does not match (MSR=%ld, TSC=%ld)",
+		    (t2 - t1) * 100, (r2 - r1) * 1000000000 / tsc_freq);
+}
+
+int main(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct ucall uc;
+	vm_vaddr_t tsc_page_gva;
+	int stage;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+	tsc_page_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+	TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
+		"TSC page has to be page aligned\n");
+	vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
+
+	host_check_tsc_msr_rdtsc(vm);
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+				  __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			/* Keep in sync with guest_main() */
+			TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+				    stage);
+			goto out;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage,
+			    "Stage %d: Unexpected register values vmexit, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+		/* Reset kvmclock triggering TSC page update */
+		if (stage == 7 || stage == 8 || stage == 10) {
+			struct kvm_clock_data clock = {0};
+
+			vm_ioctl(vm, KVM_SET_CLOCK, &clock);
+		}
+	}
+
+out:
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
new file mode 100644
index 000000000000..12c558fc8074
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_SET_BOOT_CPU_ID works as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE /* for program_invocation_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 N_VCPU 2
+#define VCPU_ID0 0
+#define VCPU_ID1 1
+
+static uint32_t get_bsp_flag(void)
+{
+	return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP;
+}
+
+static void guest_bsp_vcpu(void *arg)
+{
+	GUEST_SYNC(1);
+
+	GUEST_ASSERT(get_bsp_flag() != 0);
+
+	GUEST_DONE();
+}
+
+static void guest_not_bsp_vcpu(void *arg)
+{
+	GUEST_SYNC(1);
+
+	GUEST_ASSERT(get_bsp_flag() == 0);
+
+	GUEST_DONE();
+}
+
+static void test_set_boot_busy(struct kvm_vm *vm)
+{
+	int res;
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0);
+	TEST_ASSERT(res == -1 && errno == EBUSY,
+			"KVM_SET_BOOT_CPU_ID set while running vm");
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct ucall uc;
+	int stage;
+
+	for (stage = 0; stage < 2; stage++) {
+
+		vcpu_run(vm, vcpuid);
+
+		switch (get_ucall(vm, vcpuid, &uc)) {
+		case UCALL_SYNC:
+			TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+					uc.args[1] == stage + 1,
+					"Stage %d: Unexpected register values vmexit, got %lx",
+					stage + 1, (ulong)uc.args[1]);
+			test_set_boot_busy(vm);
+			break;
+		case UCALL_DONE:
+			TEST_ASSERT(stage == 1,
+					"Expected GUEST_DONE in stage 2, got stage %d",
+					stage);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx",
+						(const char *)uc.args[0], __FILE__,
+						uc.args[1], uc.args[2], uc.args[3]);
+		default:
+			TEST_ASSERT(false, "Unexpected exit: %s",
+					exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+		}
+	}
+}
+
+static struct kvm_vm *create_vm(void)
+{
+	struct kvm_vm *vm;
+	uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2;
+	uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+
+	pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages);
+	vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_create_irqchip(vm);
+
+	return vm;
+}
+
+static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code)
+{
+	if (bsp_code)
+		vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu);
+	else
+		vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu);
+
+	vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+}
+
+static void run_vm_bsp(uint32_t bsp_vcpu)
+{
+	struct kvm_vm *vm;
+	bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1;
+
+	vm = create_vm();
+
+	if (is_bsp_vcpu1)
+		vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+
+	add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1);
+	add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1);
+
+	run_vcpu(vm, VCPU_ID0);
+	run_vcpu(vm, VCPU_ID1);
+
+	kvm_vm_free(vm);
+}
+
+static void check_set_bsp_busy(void)
+{
+	struct kvm_vm *vm;
+	int res;
+
+	vm = create_vm();
+
+	add_x86_vcpu(vm, VCPU_ID0, true);
+	add_x86_vcpu(vm, VCPU_ID1, false);
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+	TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu");
+
+	run_vcpu(vm, VCPU_ID0);
+	run_vcpu(vm, VCPU_ID1);
+
+	res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+	TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu");
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) {
+		print_skip("set_boot_cpu_id not available");
+		return 0;
+	}
+
+	run_vm_bsp(VCPU_ID0);
+	run_vm_bsp(VCPU_ID1);
+	run_vm_bsp(VCPU_ID0);
+
+	check_set_bsp_busy();
+}