@@ -200,6 +200,17 @@ the list of KVM VCPU features and their descriptions.
adjustment, also restoring the legacy (pre-5.0)
behavior.
+ kvm-steal-time Since v5.2, kvm-steal-time is enabled by
+ default when KVM is enabled, the feature is
+ supported, and the guest is 64-bit.
+
+ When kvm-steal-time is enabled a 64-bit guest
+ can account for time its CPUs were not running
+ due to the host not scheduling the corresponding
+ VCPU threads. The accounting statistics may
+ influence the guest scheduler behavior and/or be
+ exposed to the guest userspace.
+
SVE CPU Properties
==================
@@ -151,6 +151,7 @@ static const MemMapEntry base_memmap[] = {
[VIRT_PCDIMM_ACPI] = { 0x09070000, MEMORY_HOTPLUG_IO_LEN },
[VIRT_ACPI_GED] = { 0x09080000, ACPI_GED_EVT_SEL_LEN },
[VIRT_NVDIMM_ACPI] = { 0x09090000, NVDIMM_ACPI_IO_LEN},
+ [VIRT_PVTIME] = { 0x090a0000, 0x00010000 },
[VIRT_MMIO] = { 0x0a000000, 0x00000200 },
/* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
[VIRT_PLATFORM_BUS] = { 0x0c000000, 0x02000000 },
@@ -1666,15 +1667,39 @@ static void finalize_gic_version(VirtMachineState *vms)
* virt_cpu_post_init() must be called after the CPUs have
* been realized and the GIC has been created.
*/
-static void virt_cpu_post_init(VirtMachineState *vms)
+static void virt_cpu_post_init(VirtMachineState *vms, int max_cpus,
+ MemoryRegion *sysmem)
{
- bool aarch64, pmu;
+ bool aarch64, pmu, steal_time;
CPUState *cpu;
aarch64 = object_property_get_bool(OBJECT(first_cpu), "aarch64", NULL);
pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL);
+ steal_time = object_property_get_bool(OBJECT(first_cpu),
+ "kvm-steal-time", NULL);
if (kvm_enabled()) {
+ hwaddr pvtime_reg_base = vms->memmap[VIRT_PVTIME].base;
+ hwaddr pvtime_reg_size = vms->memmap[VIRT_PVTIME].size;
+
+ if (steal_time) {
+ MemoryRegion *pvtime = g_new(MemoryRegion, 1);
+ hwaddr pvtime_size = max_cpus * PVTIME_SIZE_PER_CPU;
+
+ /* The memory region size must be a multiple of host page size. */
+ pvtime_size = REAL_HOST_PAGE_ALIGN(pvtime_size);
+
+ if (pvtime_size > pvtime_reg_size) {
+ error_report("pvtime requires a %ld byte memory region for "
+ "%d CPUs, but only %ld has been reserved",
+ pvtime_size, max_cpus, pvtime_reg_size);
+ exit(1);
+ }
+
+ memory_region_init_ram(pvtime, NULL, "pvtime", pvtime_size, NULL);
+ memory_region_add_subregion(sysmem, pvtime_reg_base, pvtime);
+ }
+
CPU_FOREACH(cpu) {
if (pmu) {
assert(arm_feature(&ARM_CPU(cpu)->env, ARM_FEATURE_PMU));
@@ -1683,6 +1708,10 @@ static void virt_cpu_post_init(VirtMachineState *vms)
}
kvm_arm_pmu_init(cpu);
}
+ if (steal_time) {
+ kvm_arm_pvtime_init(cpu, pvtime_reg_base +
+ cpu->cpu_index * PVTIME_SIZE_PER_CPU);
+ }
}
} else {
if (aarch64 && vms->highmem) {
@@ -1853,6 +1882,11 @@ static void machvirt_init(MachineState *machine)
object_property_set_bool(cpuobj, "kvm-no-adjvtime", true, NULL);
}
+ if (vmc->no_kvm_steal_time &&
+ object_property_find(cpuobj, "kvm-steal-time")) {
+ object_property_set_bool(cpuobj, "kvm-steal-time", false, NULL);
+ }
+
if (vmc->no_pmu && object_property_find(cpuobj, "pmu")) {
object_property_set_bool(cpuobj, "pmu", false, NULL);
}
@@ -1924,7 +1958,7 @@ static void machvirt_init(MachineState *machine)
create_gic(vms);
- virt_cpu_post_init(vms);
+ virt_cpu_post_init(vms, possible_cpus->len, sysmem);
fdt_add_pmu_nodes(vms);
@@ -2566,8 +2600,11 @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 2)
static void virt_machine_5_1_options(MachineClass *mc)
{
+ VirtMachineClass *vmc = VIRT_MACHINE_CLASS(OBJECT_CLASS(mc));
+
virt_machine_5_2_options(mc);
compat_props_add(mc->compat_props, hw_compat_5_1, hw_compat_5_1_len);
+ vmc->no_kvm_steal_time = true;
}
DEFINE_VIRT_MACHINE(5, 1)
@@ -54,6 +54,9 @@
#define PPI(irq) ((irq) + 16)
+/* See Linux kernel arch/arm64/include/asm/pvclock-abi.h */
+#define PVTIME_SIZE_PER_CPU 64
+
enum {
VIRT_FLASH,
VIRT_MEM,
@@ -81,6 +84,7 @@ enum {
VIRT_PCDIMM_ACPI,
VIRT_ACPI_GED,
VIRT_NVDIMM_ACPI,
+ VIRT_PVTIME,
VIRT_LOWMEMMAP_LAST,
};
@@ -126,6 +130,7 @@ struct VirtMachineClass {
bool no_highmem_ecam;
bool no_ged; /* Machines < 4.2 has no support for ACPI GED device */
bool kvm_no_adjvtime;
+ bool no_kvm_steal_time;
bool acpi_expose_flash;
};
@@ -1310,6 +1310,14 @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp)
return;
}
}
+
+ if (kvm_enabled()) {
+ kvm_arm_steal_time_finalize(cpu, &local_err);
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ }
}
static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
@@ -24,6 +24,7 @@
#include "hw/registerfields.h"
#include "cpu-qom.h"
#include "exec/cpu-defs.h"
+#include "qapi/qapi-types-common.h"
/* ARM processors have a weak memory model */
#define TCG_GUEST_DEFAULT_MO (0)
@@ -863,6 +864,9 @@ struct ARMCPU {
bool kvm_vtime_dirty;
uint64_t kvm_vtime;
+ /* KVM steal time */
+ OnOffAuto kvm_steal_time;
+
/* Uniprocessor system with MP extensions */
bool mp_is_up;
@@ -192,6 +192,16 @@ static void kvm_no_adjvtime_set(Object *obj, bool value, Error **errp)
ARM_CPU(obj)->kvm_adjvtime = !value;
}
+static bool kvm_steal_time_get(Object *obj, Error **errp)
+{
+ return ARM_CPU(obj)->kvm_steal_time != ON_OFF_AUTO_OFF;
+}
+
+static void kvm_steal_time_set(Object *obj, bool value, Error **errp)
+{
+ ARM_CPU(obj)->kvm_steal_time = value ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
+}
+
/* KVM VCPU properties should be prefixed with "kvm-". */
void kvm_arm_add_vcpu_properties(Object *obj)
{
@@ -207,6 +217,12 @@ void kvm_arm_add_vcpu_properties(Object *obj)
"the virtual counter. VM stopped time "
"will be counted.");
}
+
+ cpu->kvm_steal_time = ON_OFF_AUTO_AUTO;
+ object_property_add_bool(obj, "kvm-steal-time", kvm_steal_time_get,
+ kvm_steal_time_set);
+ object_property_set_description(obj, "kvm-steal-time",
+ "Set off to disable KVM steal time.");
}
bool kvm_arm_pmu_supported(void)
@@ -17,6 +17,7 @@
#include <linux/kvm.h>
#include "qemu-common.h"
+#include "qapi/error.h"
#include "cpu.h"
#include "qemu/timer.h"
#include "qemu/error-report.h"
@@ -397,19 +398,20 @@ static CPUWatchpoint *find_hw_watchpoint(CPUState *cpu, target_ulong addr)
return NULL;
}
-static bool kvm_arm_pmu_set_attr(CPUState *cs, struct kvm_device_attr *attr)
+static bool kvm_arm_set_device_attr(CPUState *cs, struct kvm_device_attr *attr,
+ const char *name)
{
int err;
err = kvm_vcpu_ioctl(cs, KVM_HAS_DEVICE_ATTR, attr);
if (err != 0) {
- error_report("PMU: KVM_HAS_DEVICE_ATTR: %s", strerror(-err));
+ error_report("%s: KVM_HAS_DEVICE_ATTR: %s", name, strerror(-err));
return false;
}
err = kvm_vcpu_ioctl(cs, KVM_SET_DEVICE_ATTR, attr);
if (err != 0) {
- error_report("PMU: KVM_SET_DEVICE_ATTR: %s", strerror(-err));
+ error_report("%s: KVM_SET_DEVICE_ATTR: %s", name, strerror(-err));
return false;
}
@@ -426,7 +428,7 @@ void kvm_arm_pmu_init(CPUState *cs)
if (!ARM_CPU(cs)->has_pmu) {
return;
}
- if (!kvm_arm_pmu_set_attr(cs, &attr)) {
+ if (!kvm_arm_set_device_attr(cs, &attr, "PMU")) {
error_report("failed to init PMU");
abort();
}
@@ -443,12 +445,29 @@ void kvm_arm_pmu_set_irq(CPUState *cs, int irq)
if (!ARM_CPU(cs)->has_pmu) {
return;
}
- if (!kvm_arm_pmu_set_attr(cs, &attr)) {
+ if (!kvm_arm_set_device_attr(cs, &attr, "PMU")) {
error_report("failed to set irq for PMU");
abort();
}
}
+void kvm_arm_pvtime_init(CPUState *cs, uint64_t ipa)
+{
+ struct kvm_device_attr attr = {
+ .group = KVM_ARM_VCPU_PVTIME_CTRL,
+ .attr = KVM_ARM_VCPU_PVTIME_IPA,
+ .addr = (uint64_t)&ipa,
+ };
+
+ if (ARM_CPU(cs)->kvm_steal_time == ON_OFF_AUTO_OFF) {
+ return;
+ }
+ if (!kvm_arm_set_device_attr(cs, &attr, "PVTIME IPA")) {
+ error_report("failed to init PVTIME IPA");
+ abort();
+ }
+}
+
static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id)
{
uint64_t ret;
@@ -651,6 +670,36 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
return true;
}
+void kvm_arm_steal_time_finalize(ARMCPU *cpu, Error **errp)
+{
+ bool has_steal_time = kvm_arm_steal_time_supported();
+
+ if (cpu->kvm_steal_time == ON_OFF_AUTO_AUTO) {
+ if (!has_steal_time || !arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+ cpu->kvm_steal_time = ON_OFF_AUTO_OFF;
+ } else {
+ cpu->kvm_steal_time = ON_OFF_AUTO_ON;
+ }
+ } else if (cpu->kvm_steal_time == ON_OFF_AUTO_ON) {
+ if (!has_steal_time) {
+ error_setg(errp, "'kvm-steal-time' cannot be enabled "
+ "on this host");
+ return;
+ } else if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) {
+ /*
+ * DEN0057A chapter 2 says "This specification only covers
+ * systems in which the Execution state of the hypervisor
+ * as well as EL1 of virtual machines is AArch64.". And,
+ * to ensure that, the smc/hvc calls are only specified as
+ * smc64/hvc64.
+ */
+ error_setg(errp, "'kvm-steal-time' cannot be enabled "
+ "for AArch32 guests");
+ return;
+ }
+ }
+}
+
bool kvm_arm_aarch32_supported(void)
{
return kvm_check_extension(kvm_state, KVM_CAP_ARM_EL1_32BIT);
@@ -661,6 +710,11 @@ bool kvm_arm_sve_supported(void)
return kvm_check_extension(kvm_state, KVM_CAP_ARM_SVE);
}
+bool kvm_arm_steal_time_supported(void)
+{
+ return kvm_check_extension(kvm_state, KVM_CAP_STEAL_TIME);
+}
+
QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1);
void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map)
@@ -267,6 +267,24 @@ void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu);
*/
void kvm_arm_add_vcpu_properties(Object *obj);
+/**
+ * kvm_arm_steal_time_finalize:
+ * @cpu: ARMCPU for which to finalize kvm-steal-time
+ * @errp: Pointer to Error* for error propagation
+ *
+ * Validate the kvm-steal-time property selection and set its default
+ * based on KVM support and guest configuration.
+ */
+void kvm_arm_steal_time_finalize(ARMCPU *cpu, Error **errp);
+
+/**
+ * kvm_arm_steal_time_supported:
+ *
+ * Returns: true if KVM can enable steal time reporting
+ * and false otherwise.
+ */
+bool kvm_arm_steal_time_supported(void);
+
/**
* kvm_arm_aarch32_supported:
*
@@ -340,6 +358,16 @@ int kvm_arm_vgic_probe(void);
void kvm_arm_pmu_set_irq(CPUState *cs, int irq);
void kvm_arm_pmu_init(CPUState *cs);
+
+/**
+ * kvm_arm_pvtime_init:
+ * @cs: CPUState
+ * @ipa: Per-vcpu guest physical base address of the pvtime structures
+ *
+ * Initializes PVTIME for the VCPU, setting the PVTIME IPA to @ipa.
+ */
+void kvm_arm_pvtime_init(CPUState *cs, uint64_t ipa);
+
int kvm_arm_set_irq(int cpu, int irqtype, int irq, int level);
#else
@@ -363,6 +391,11 @@ static inline bool kvm_arm_sve_supported(void)
return false;
}
+static inline bool kvm_arm_steal_time_supported(void)
+{
+ return false;
+}
+
/*
* These functions should never actually be called without KVM support.
*/
@@ -396,6 +429,16 @@ static inline void kvm_arm_pmu_init(CPUState *cs)
g_assert_not_reached();
}
+static inline void kvm_arm_pvtime_init(CPUState *cs, uint64_t ipa)
+{
+ g_assert_not_reached();
+}
+
+static inline void kvm_arm_steal_time_finalize(ARMCPU *cpu, Error **errp)
+{
+ g_assert_not_reached();
+}
+
static inline void kvm_arm_sve_get_vls(CPUState *cs, unsigned long *map)
{
g_assert_not_reached();
@@ -103,7 +103,7 @@ static const char *cpu_model_advertised_features[] = {
"sve128", "sve256", "sve384", "sve512",
"sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280",
"sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048",
- "kvm-no-adjvtime",
+ "kvm-no-adjvtime", "kvm-steal-time",
NULL
};
@@ -452,6 +452,7 @@ static void test_query_cpu_model_expansion(const void *data)
assert_set_feature(qts, "max", "pmu", true);
assert_has_not_feature(qts, "max", "kvm-no-adjvtime");
+ assert_has_not_feature(qts, "max", "kvm-steal-time");
if (g_str_equal(qtest_get_arch(), "aarch64")) {
assert_has_feature_enabled(qts, "max", "aarch64");
@@ -493,6 +494,7 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
assert_set_feature(qts, "host", "kvm-no-adjvtime", false);
if (g_str_equal(qtest_get_arch(), "aarch64")) {
+ bool kvm_supports_steal_time;
bool kvm_supports_sve;
char max_name[8], name[8];
uint32_t max_vq, vq;
@@ -500,6 +502,10 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
QDict *resp;
char *error;
+ assert_error(qts, "cortex-a15",
+ "We cannot guarantee the CPU type 'cortex-a15' works "
+ "with KVM on this host", NULL);
+
assert_has_feature_enabled(qts, "host", "aarch64");
/* Enabling and disabling pmu should always work. */
@@ -507,16 +513,26 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
assert_set_feature(qts, "host", "pmu", false);
assert_set_feature(qts, "host", "pmu", true);
- assert_error(qts, "cortex-a15",
- "We cannot guarantee the CPU type 'cortex-a15' works "
- "with KVM on this host", NULL);
-
+ /*
+ * Some features would be enabled by default, but they're disabled
+ * because this instance of KVM doesn't support them. Test that the
+ * features are present, and, when enabled, issue further tests.
+ */
+ assert_has_feature(qts, "host", "kvm-steal-time");
assert_has_feature(qts, "host", "sve");
+
resp = do_query_no_props(qts, "host");
+ kvm_supports_steal_time = resp_get_feature(resp, "kvm-steal-time");
kvm_supports_sve = resp_get_feature(resp, "sve");
vls = resp_get_sve_vls(resp);
qobject_unref(resp);
+ if (kvm_supports_steal_time) {
+ /* If we have steal-time then we should be able to toggle it. */
+ assert_set_feature(qts, "host", "kvm-steal-time", false);
+ assert_set_feature(qts, "host", "kvm-steal-time", true);
+ }
+
if (kvm_supports_sve) {
g_assert(vls != 0);
max_vq = 64 - __builtin_clzll(vls);
@@ -577,6 +593,7 @@ static void test_query_cpu_model_expansion_kvm(const void *data)
assert_has_not_feature(qts, "host", "aarch64");
assert_has_not_feature(qts, "host", "pmu");
assert_has_not_feature(qts, "host", "sve");
+ assert_has_not_feature(qts, "host", "kvm-steal-time");
}
qtest_quit(qts);