selftests: KVM: Introduce system counter offset test

Introduce a KVM selftest to verify that userspace manipulation of the
TSC (via the new vCPU attribute) results in the correct behavior within
the guest.

Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Message-Id: <20210916181555.973085-6-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 161 insertions, 14 deletions

diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst
index 3b399d727c11..60a29972d3f1 100644
--- a/Documentation/virt/kvm/devices/vcpu.rst
+++ b/Documentation/virt/kvm/devices/vcpu.rst
@@ -184,37 +184,50 @@ TSC is then derived by the following equation:
 
   guest_tsc = host_tsc + KVM_VCPU_TSC_OFFSET
 
-This attribute is useful for the precise migration of a guest's TSC. The
-following describes a possible algorithm to use for the migration of a
-guest's TSC:
+This attribute is useful to adjust the guest's TSC on live migration,
+so that the TSC counts the time during which the VM was paused. The
+following describes a possible algorithm to use for this purpose.
 
 From the source VMM process:
 
-1. Invoke the KVM_GET_CLOCK ioctl to record the host TSC (t_0),
-   kvmclock nanoseconds (k_0), and realtime nanoseconds (r_0).
+1. Invoke the KVM_GET_CLOCK ioctl to record the host TSC (tsc_src),
+   kvmclock nanoseconds (guest_src), and host CLOCK_REALTIME nanoseconds
+   (host_src).
 
 2. Read the KVM_VCPU_TSC_OFFSET attribute for every vCPU to record the
-   guest TSC offset (off_n).
+   guest TSC offset (ofs_src[i]).
 
 3. Invoke the KVM_GET_TSC_KHZ ioctl to record the frequency of the
    guest's TSC (freq).
 
 From the destination VMM process:
 
-4. Invoke the KVM_SET_CLOCK ioctl, providing the kvmclock nanoseconds
-   (k_0) and realtime nanoseconds (r_0) in their respective fields.
-   Ensure that the KVM_CLOCK_REALTIME flag is set in the provided
-   structure. KVM will advance the VM's kvmclock to account for elapsed
-   time since recording the clock values.
+4. Invoke the KVM_SET_CLOCK ioctl, providing the source nanoseconds from
+   kvmclock (guest_src) and CLOCK_REALTIME (host_src) in their respective
+   fields.  Ensure that the KVM_CLOCK_REALTIME flag is set in the provided
+   structure.
 
-5. Invoke the KVM_GET_CLOCK ioctl to record the host TSC (t_1) and
-   kvmclock nanoseconds (k_1).
+   KVM will advance the VM's kvmclock to account for elapsed time since
+   recording the clock values.  Note that this will cause problems in
+   the guest (e.g., timeouts) unless CLOCK_REALTIME is synchronized
+   between the source and destination, and a reasonably short time passes
+   between the source pausing the VMs and the destination executing
+   steps 4-7.
+
+5. Invoke the KVM_GET_CLOCK ioctl to record the host TSC (tsc_dest) and
+   kvmclock nanoseconds (guest_dest).
 
 6. Adjust the guest TSC offsets for every vCPU to account for (1) time
    elapsed since recording state and (2) difference in TSCs between the
    source and destination machine:
 
-   new_off_n = t_0 + off_n + (k_1 - k_0) * freq - t_1
+   ofs_dst[i] = ofs_src[i] -
+     (guest_src - guest_dest) * freq +
+     (tsc_src - tsc_dest)
+
+   ("ofs[i] + tsc - guest * freq" is the guest TSC value corresponding to
+   a time of 0 in kvmclock.  The above formula ensures that it is the
+   same on the destination as it was on the source).
 
 7. Write the KVM_VCPU_TSC_OFFSET attribute for every vCPU with the
    respective value derived in the previous step.
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 4bcff9c1a524..fdd13fbdcc8f 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -54,3 +54,4 @@
 /set_memory_region_test
 /steal_time
 /kvm_binary_stats_test
+/system_counter_offset_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3995940d0011..fd20f271aac0 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += rseq_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
+TEST_GEN_PROGS_x86_64 += system_counter_offset_test
 
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
new file mode 100644
index 000000000000..b337bbbfa41f
--- /dev/null
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Google LLC.
+ *
+ * Tests for adjusting the system counter from userspace
+ */
+#include <asm/kvm_para.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <time.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+#ifdef __x86_64__
+
+struct test_case {
+	uint64_t tsc_offset;
+};
+
+static struct test_case test_cases[] = {
+	{ 0 },
+	{ 180 * NSEC_PER_SEC },
+	{ -180 * NSEC_PER_SEC },
+};
+
+static void check_preconditions(struct kvm_vm *vm)
+{
+	if (!_vcpu_has_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL, KVM_VCPU_TSC_OFFSET))
+		return;
+
+	print_skip("KVM_VCPU_TSC_OFFSET not supported; skipping test");
+	exit(KSFT_SKIP);
+}
+
+static void setup_system_counter(struct kvm_vm *vm, struct test_case *test)
+{
+	vcpu_access_device_attr(vm, VCPU_ID, KVM_VCPU_TSC_CTRL,
+				KVM_VCPU_TSC_OFFSET, &test->tsc_offset, true);
+}
+
+static uint64_t guest_read_system_counter(struct test_case *test)
+{
+	return rdtsc();
+}
+
+static uint64_t host_read_guest_system_counter(struct test_case *test)
+{
+	return rdtsc() + test->tsc_offset;
+}
+
+#else /* __x86_64__ */
+
+#error test not implemented for this architecture!
+
+#endif
+
+#define GUEST_SYNC_CLOCK(__stage, __val)			\
+		GUEST_SYNC_ARGS(__stage, __val, 0, 0, 0)
+
+static void guest_main(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		struct test_case *test = &test_cases[i];
+
+		GUEST_SYNC_CLOCK(i, guest_read_system_counter(test));
+	}
+}
+
+static void handle_sync(struct ucall *uc, uint64_t start, uint64_t end)
+{
+	uint64_t obs = uc->args[2];
+
+	TEST_ASSERT(start <= obs && obs <= end,
+		    "unexpected system counter value: %"PRIu64" expected range: [%"PRIu64", %"PRIu64"]",
+		    obs, start, end);
+
+	pr_info("system counter value: %"PRIu64" expected range [%"PRIu64", %"PRIu64"]\n",
+		obs, start, end);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+		  __FILE__, uc->args[1]);
+}
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	uint64_t start, end;
+	struct ucall uc;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		struct test_case *test = &test_cases[i];
+
+		setup_system_counter(vm, test);
+		start = host_read_guest_system_counter(test);
+		vcpu_run(vm, VCPU_ID);
+		end = host_read_guest_system_counter(test);
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			handle_sync(&uc, start, end);
+			break;
+		case UCALL_ABORT:
+			handle_abort(&uc);
+			return;
+		default:
+			TEST_ASSERT(0, "unhandled ucall %ld\n",
+				    get_ucall(vm, VCPU_ID, &uc));
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	check_preconditions(vm);
+	ucall_init(vm, NULL);
+
+	enter_guest(vm);
+	kvm_vm_free(vm);
+}