static int cstate_cpu_init(unsigned int cpu)
{
unsigned int target;
/*
* If this is the first online thread of that core, set it in
* the core cpu mask as the designated reader.
*/
target = cpumask_any_and(&cstate_core_cpu_mask,
topology_sibling_cpumask(cpu));
if (has_cstate_core && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_core_cpu_mask);
/*
* If this is the first online thread of that package, set it
* in the package cpu mask as the designated reader.
*/
target = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_core_cpumask(cpu));
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
return 0;
}
void set_cpu_sibling_map(int cpu)
{
bool has_smt = smp_num_siblings > 1;
bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct cpuinfo_x86 *o;
int i;
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
if (!has_mp) {
cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
c->booted_cores = 1;
return;
}
for_each_cpu(i, cpu_sibling_setup_mask) {
o = &cpu_data(i);
if ((i == cpu) || (has_smt && match_smt(c, o)))
link_mask(topology_sibling_cpumask, cpu, i);
if ((i == cpu) || (has_mp && match_llc(c, o)))
link_mask(cpu_llc_shared_mask, cpu, i);
}
/*
* Check if exiting cpu is the designated reader. If so migrate the
* events when there is a valid target available
*/
static int cstate_cpu_exit(unsigned int cpu)
{
unsigned int target;
if (has_cstate_core &&
cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) {
target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
/* Migrate events if there is a valid target */
if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &cstate_core_cpu_mask);
perf_pmu_migrate_context(&cstate_core_pmu, cpu, target);
}
}
if (has_cstate_pkg &&
cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
/* Migrate events if there is a valid target */
if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
}
}
return 0;
}
/*
* Store and check the TSC ADJUST MSR if available
*/
bool tsc_store_and_check_tsc_adjust(bool bootcpu)
{
struct tsc_adjust *ref, *cur = this_cpu_ptr(&tsc_adjust);
unsigned int refcpu, cpu = smp_processor_id();
struct cpumask *mask;
s64 bootval;
if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
return false;
rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
cur->bootval = bootval;
cur->nextcheck = jiffies + HZ;
cur->warned = false;
/*
* Check whether this CPU is the first in a package to come up. In
* this case do not check the boot value against another package
* because the new package might have been physically hotplugged,
* where TSC_ADJUST is expected to be different. When called on the
* boot CPU topology_core_cpumask() might not be available yet.
*/
mask = topology_core_cpumask(cpu);
refcpu = mask ? cpumask_any_but(mask, cpu) : nr_cpu_ids;
if (refcpu >= nr_cpu_ids) {
tsc_sanitize_first_cpu(cur, bootval, smp_processor_id(),
bootcpu);
return false;
}
ref = per_cpu_ptr(&tsc_adjust, refcpu);
/*
* Compare the boot value and complain if it differs in the
* package.
*/
if (bootval != ref->bootval) {
pr_warn(FW_BUG "TSC ADJUST differs: Reference CPU%u: %lld CPU%u: %lld\n",
refcpu, ref->bootval, cpu, bootval);
}
/*
* The TSC_ADJUST values in a package must be the same. If the boot
* value on this newly upcoming CPU differs from the adjustment
* value of the already online CPU in this package, set it to that
* adjusted value.
*/
if (bootval != ref->adjusted) {
pr_warn("TSC ADJUST synchronize: Reference CPU%u: %lld CPU%u: %lld\n",
refcpu, ref->adjusted, cpu, bootval);
cur->adjusted = ref->adjusted;
wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted);
}
/*
* We have the TSCs forced to be in sync on this package. Skip sync
* test:
*/
return true;
}
/*
* Get CPU information for use by the procfs.
*/
static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
unsigned int cpu)
{
#ifdef CONFIG_SMP
seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
seq_printf(m, "siblings\t: %d\n",
cpumask_weight(topology_core_cpumask(cpu)));
seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
seq_printf(m, "apicid\t\t: %d\n", c->apicid);
seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid);
#endif
}
/* Update distances based on topology */
for_each_cpu(cpu, update_mask) {
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_sibling_cpumask(cpu), 1))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_core_cpumask(cpu), 2))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
cpumask_of_node(cpu_to_node(cpu)), 3))
continue;
/* We could continue into NUMA node distances, but for now
* we give up.
*/
}
static int cstate_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config;
int cpu;
if (event->attr.type != event->pmu->type)
return -ENOENT;
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
event->attr.exclude_hv ||
event->attr.exclude_idle ||
event->attr.exclude_host ||
event->attr.exclude_guest ||
event->attr.sample_period) /* no sampling */
return -EINVAL;
if (event->cpu < 0)
return -EINVAL;
if (event->pmu == &cstate_core_pmu) {
if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
return -EINVAL;
if (!core_msr[cfg].attr)
return -EINVAL;
event->hw.event_base = core_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_core_cpu_mask,
topology_sibling_cpumask(event->cpu));
} else if (event->pmu == &cstate_pkg_pmu) {
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
if (!pkg_msr[cfg].attr)
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_core_cpumask(event->cpu));
} else {
return -ENOENT;
}
if (cpu >= nr_cpu_ids)
return -ENODEV;
event->cpu = cpu;
event->hw.config = cfg;
event->hw.idx = -1;
return 0;
}
/* Per-CPU initialization */
static int bL_cpufreq_init(struct cpufreq_policy *policy)
{
u32 cur_cluster = cpu_to_cluster(policy->cpu);
struct device *cpu_dev;
int ret;
cpu_dev = get_cpu_device(policy->cpu);
if (!cpu_dev) {
pr_err("%s: failed to get cpu%d device\n", __func__,
policy->cpu);
return -ENODEV;
}
ret = get_cluster_clk_and_freq_table(cpu_dev);
if (ret)
return ret;
ret = cpufreq_table_validate_and_show(policy, freq_table[cur_cluster]);
if (ret) {
dev_err(cpu_dev, "CPU %d, cluster: %d invalid freq table\n",
policy->cpu, cur_cluster);
put_cluster_clk_and_freq_table(cpu_dev);
return ret;
}
if (cur_cluster < MAX_CLUSTERS) {
int cpu;
cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
for_each_cpu(cpu, policy->cpus)
per_cpu(physical_cluster, cpu) = cur_cluster;
} else {
/* Assumption: during init, we are always running on A15 */
per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
}
if (arm_bL_ops->get_transition_latency)
policy->cpuinfo.transition_latency =
arm_bL_ops->get_transition_latency(cpu_dev);
else
policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
if (is_bL_switching_enabled())
per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu);
dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
return 0;
}
static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
unsigned int i;
unsigned int valid_states = 0;
unsigned int cpu = policy->cpu;
struct acpi_cpufreq_data *data;
unsigned int result = 0;
struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
struct acpi_processor_performance *perf;
#ifdef CONFIG_SMP
static int blacklisted;
#endif
pr_debug("acpi_cpufreq_cpu_init\n");
#ifdef CONFIG_SMP
if (blacklisted)
return blacklisted;
blacklisted = acpi_cpufreq_blacklist(c);
if (blacklisted)
return blacklisted;
#endif
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
if (!zalloc_cpumask_var(&data->freqdomain_cpus, GFP_KERNEL)) {
result = -ENOMEM;
goto err_free;
}
perf = per_cpu_ptr(acpi_perf_data, cpu);
data->acpi_perf_cpu = cpu;
policy->driver_data = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
result = acpi_processor_register_performance(perf, cpu);
if (result)
goto err_free_mask;
policy->shared_type = perf->shared_type;
/*
* Will let policy->cpus know about dependency only when software
* coordination is required.
*/
if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
cpumask_copy(policy->cpus, perf->shared_cpu_map);
}
cpumask_copy(data->freqdomain_cpus, perf->shared_cpu_map);
#ifdef CONFIG_SMP
dmi_check_system(sw_any_bug_dmi_table);
if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
}
if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
cpumask_clear(policy->cpus);
cpumask_set_cpu(cpu, policy->cpus);
cpumask_copy(data->freqdomain_cpus,
topology_sibling_cpumask(cpu));
policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
pr_info_once(PFX "overriding BIOS provided _PSD data\n");
}
#endif
/* capability check */
if (perf->state_count <= 1) {
pr_debug("No P-States\n");
result = -ENODEV;
goto err_unreg;
}
if (perf->control_register.space_id != perf->status_register.space_id) {
result = -ENODEV;
goto err_unreg;
}
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 == 0xf) {
pr_debug("AMD K8 systems must use native drivers.\n");
result = -ENODEV;
goto err_unreg;
}
pr_debug("SYSTEM IO addr space\n");
data->cpu_feature = SYSTEM_IO_CAPABLE;
break;
case ACPI_ADR_SPACE_FIXED_HARDWARE:
pr_debug("HARDWARE addr space\n");
if (check_est_cpu(cpu)) {
data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
break;
}
if (check_amd_hwpstate_cpu(cpu)) {
data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
break;
}
result = -ENODEV;
goto err_unreg;
default:
pr_debug("Unknown addr space %d\n",
(u32) (perf->control_register.space_id));
result = -ENODEV;
goto err_unreg;
}
data->freq_table = kzalloc(sizeof(*data->freq_table) *
(perf->state_count+1), GFP_KERNEL);
if (!data->freq_table) {
result = -ENOMEM;
goto err_unreg;
}
/* detect transition latency */
policy->cpuinfo.transition_latency = 0;
for (i = 0; i < perf->state_count; i++) {
if ((perf->states[i].transition_latency * 1000) >
policy->cpuinfo.transition_latency)
policy->cpuinfo.transition_latency =
perf->states[i].transition_latency * 1000;
}
/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
policy->cpuinfo.transition_latency > 20 * 1000) {
policy->cpuinfo.transition_latency = 20 * 1000;
printk_once(KERN_INFO
"P-state transition latency capped at 20 uS\n");
}
/* table init */
for (i = 0; i < perf->state_count; i++) {
if (i > 0 && perf->states[i].core_frequency >=
data->freq_table[valid_states-1].frequency / 1000)
continue;
data->freq_table[valid_states].driver_data = i;
data->freq_table[valid_states].frequency =
perf->states[i].core_frequency * 1000;
valid_states++;
}
data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
perf->state = 0;
result = cpufreq_table_validate_and_show(policy, data->freq_table);
if (result)
goto err_freqfree;
if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
/*
* The core will not set policy->cur, because
* cpufreq_driver->get is NULL, so we need to set it here.
* However, we have to guess it, because the current speed is
* unknown and not detectable via IO ports.
*/
policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu);
break;
case ACPI_ADR_SPACE_FIXED_HARDWARE:
acpi_cpufreq_driver.get = get_cur_freq_on_cpu;
break;
default:
break;
}
/* notify BIOS that we exist */
acpi_processor_notify_smm(THIS_MODULE);
pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
for (i = 0; i < perf->state_count; i++)
pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n",
(i == perf->state ? '*' : ' '), i,
(u32) perf->states[i].core_frequency,
(u32) perf->states[i].power,
(u32) perf->states[i].transition_latency);
/*
* the first call to ->target() should result in us actually
* writing something to the appropriate registers.
*/
data->resume = 1;
return result;
err_freqfree:
kfree(data->freq_table);
err_unreg:
acpi_processor_unregister_performance(cpu);
err_free_mask:
free_cpumask_var(data->freqdomain_cpus);
err_free:
kfree(data);
policy->driver_data = NULL;
return result;
}
/*
* If the target CPU coming online doesn't have any of its core-siblings
* online, a timeout of 20msec will be used for the TSC-warp measurement
* loop. Otherwise a smaller timeout of 2msec will be used, as we have some
* information about this socket already (and this information grows as we
* have more and more logical-siblings in that socket).
*
* Ideally we should be able to skip the TSC sync check on the other
* core-siblings, if the first logical CPU in a socket passed the sync test.
* But as the TSC is per-logical CPU and can potentially be modified wrongly
* by the bios, TSC sync test for smaller duration should be able
* to catch such errors. Also this will catch the condition where all the
* cores in the socket doesn't get reset at the same time.
*/
static inline unsigned int loop_timeout(int cpu)
{
return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
}
