static void setup_cpu_sibling_map(int cpu)
{
if ( !zalloc_cpumask_var(&per_cpu(cpu_sibling_mask, cpu)) ||
!zalloc_cpumask_var(&per_cpu(cpu_core_mask, cpu)) )
panic("No memory for CPU sibling/core maps");
/* A CPU is a sibling with itself and is always on its own core. */
cpumask_set_cpu(cpu, per_cpu(cpu_sibling_mask, cpu));
cpumask_set_cpu(cpu, per_cpu(cpu_core_mask, cpu));
}
static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned cpu;
unsigned int i;
if (skip_ioapic_setup) {
char *m = (max_cpus == 0) ?
"The nosmp parameter is incompatible with Xen; " \
"use Xen dom0_max_vcpus=1 parameter" :
"The noapic parameter is incompatible with Xen";
xen_raw_printk(m);
panic(m);
}
xen_init_lock_cpu(0);
smp_store_cpu_info(0);
cpu_data(0).x86_max_cores = 1;
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
if (xen_smp_intr_init(0))
BUG();
if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
panic("could not allocate xen_cpu_initialized_map\n");
cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
/* Restrict the possible_map according to max_cpus. */
while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
continue;
set_cpu_possible(cpu, false);
}
for_each_possible_cpu (cpu) {
struct task_struct *idle;
if (cpu == 0)
continue;
idle = fork_idle(cpu);
if (IS_ERR(idle))
panic("failed fork for CPU %d", cpu);
set_cpu_present(cpu, true);
}
}
/*
* Update cpu_present_mask and paca(s) for a new cpu node. The wrinkle
* here is that a cpu device node may represent up to two logical cpus
* in the SMT case. We must honor the assumption in other code that
* the logical ids for sibling SMT threads x and y are adjacent, such
* that x^1 == y and y^1 == x.
*/
static int pseries_add_processor(struct device_node *np)
{
unsigned int cpu;
cpumask_var_t candidate_mask, tmp;
int err = -ENOSPC, len, nthreads, i;
const __be32 *intserv;
intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len);
if (!intserv)
return 0;
zalloc_cpumask_var(&candidate_mask, GFP_KERNEL);
zalloc_cpumask_var(&tmp, GFP_KERNEL);
nthreads = len / sizeof(u32);
for (i = 0; i < nthreads; i++)
cpumask_set_cpu(i, tmp);
cpu_maps_update_begin();
BUG_ON(!cpumask_subset(cpu_present_mask, cpu_possible_mask));
/* Get a bitmap of unoccupied slots. */
cpumask_xor(candidate_mask, cpu_possible_mask, cpu_present_mask);
if (cpumask_empty(candidate_mask)) {
/* If we get here, it most likely means that NR_CPUS is
* less than the partition's max processors setting.
*/
printk(KERN_ERR "Cannot add cpu %pOF; this system configuration"
" supports %d logical cpus.\n", np,
num_possible_cpus());
goto out_unlock;
}
while (!cpumask_empty(tmp))
if (cpumask_subset(tmp, candidate_mask))
/* Found a range where we can insert the new cpu(s) */
break;
else
cpumask_shift_left(tmp, tmp, nthreads);
if (cpumask_empty(tmp)) {
printk(KERN_ERR "Unable to find space in cpu_present_mask for"
" processor %s with %d thread(s)\n", np->name,
nthreads);
goto out_unlock;
}
for_each_cpu(cpu, tmp) {
BUG_ON(cpu_present(cpu));
set_cpu_present(cpu, true);
set_hard_smp_processor_id(cpu, be32_to_cpu(*intserv++));
}
static void __init init_irq_default_affinity(void)
{
if (!cpumask_available(irq_default_affinity))
zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
if (cpumask_empty(irq_default_affinity))
cpumask_setall(irq_default_affinity);
}
/**
* cpu_rmap_update - update CPU rmap following a change of object affinity
* @rmap: CPU rmap to update
* @index: Index of object whose affinity changed
* @affinity: New CPU affinity of object
*/
int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
const struct cpumask *affinity)
{
cpumask_var_t update_mask;
unsigned int cpu;
if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
return -ENOMEM;
/* Invalidate distance for all CPUs for which this used to be
* the nearest object. Mark those CPUs for update.
*/
for_each_online_cpu(cpu) {
if (rmap->near[cpu].index == index) {
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
cpumask_set_cpu(cpu, update_mask);
}
}
debug_print_rmap(rmap, "after invalidating old distances");
/* Set distance to 0 for all CPUs in the new affinity mask.
* Mark all CPUs within their NUMA nodes for update.
*/
for_each_cpu(cpu, affinity) {
rmap->near[cpu].index = index;
rmap->near[cpu].dist = 0;
cpumask_or(update_mask, update_mask,
cpumask_of_node(cpu_to_node(cpu)));
}
/**
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
*
* Return: -ENOMEM on memory allocation failure.
*/
int cpupri_init(struct cpupri *cp)
{
int i;
memset(cp, 0, sizeof(*cp));
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
atomic_set(&vec->count, 0);
if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
goto cleanup;
}
cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
if (!cp->cpu_to_pri)
goto cleanup;
for_each_possible_cpu(i)
cp->cpu_to_pri[i] = CPUPRI_INVALID;
return 0;
cleanup:
for (i--; i >= 0; i--)
free_cpumask_var(cp->pri_to_cpu[i].mask);
return -ENOMEM;
}
void domain_update_node_affinity(struct domain *d)
{
cpumask_var_t cpumask;
cpumask_var_t online_affinity;
const cpumask_t *online;
nodemask_t nodemask = NODE_MASK_NONE;
struct vcpu *v;
unsigned int node;
if ( !zalloc_cpumask_var(&cpumask) )
return;
if ( !alloc_cpumask_var(&online_affinity) )
{
free_cpumask_var(cpumask);
return;
}
online = cpupool_online_cpumask(d->cpupool);
spin_lock(&d->node_affinity_lock);
for_each_vcpu ( d, v )
{
cpumask_and(online_affinity, v->cpu_affinity, online);
cpumask_or(cpumask, cpumask, online_affinity);
}
static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned cpu;
unsigned int i;
xen_init_lock_cpu(0);
smp_store_cpu_info(0);
cpu_data(0).x86_max_cores = 1;
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
}
set_cpu_sibling_map(0);
if (xen_smp_intr_init(0))
BUG();
if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
panic("could not allocate xen_cpu_initialized_map\n");
cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
/* Restrict the possible_map according to max_cpus. */
while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
continue;
set_cpu_possible(cpu, false);
}
for_each_possible_cpu (cpu) {
struct task_struct *idle;
if (cpu == 0)
continue;
idle = fork_idle(cpu);
if (IS_ERR(idle))
panic("failed fork for CPU %d", cpu);
set_cpu_present(cpu, true);
}
}
static void __init init_irq_default_affinity(void)
{
#ifdef CONFIG_CPUMASK_OFFSTACK
if (!irq_default_affinity)
zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
#endif
if (cpumask_empty(irq_default_affinity))
cpumask_setall(irq_default_affinity);
}
static struct cpupool *alloc_cpupool_struct(void)
{
struct cpupool *c = xzalloc(struct cpupool);
if ( !c || !zalloc_cpumask_var(&c->cpu_valid) )
{
xfree(c);
c = NULL;
}
else if ( !zalloc_cpumask_var(&c->cpu_suspended) )
{
free_cpumask_var(c->cpu_valid);
xfree(c);
c = NULL;
}
return c;
}
long init_domain_proc_info(struct domain_proc_info* m,
int num_cpus, int num_domains)
{
int i;
int num_alloced_cpu_masks = 0;
int num_alloced_domain_masks = 0;
m->cpu_to_domains =
kmalloc(sizeof(*(m->cpu_to_domains))*num_cpus,
GFP_ATOMIC);
if(!m->cpu_to_domains)
goto failure;
m->domain_to_cpus =
kmalloc(sizeof(*(m->domain_to_cpus))*num_domains,
GFP_ATOMIC);
if(!m->domain_to_cpus)
goto failure;
for(i = 0; i < num_cpus; ++i) {
if(!zalloc_cpumask_var(&m->cpu_to_domains[i].mask, GFP_ATOMIC))
goto failure;
++num_alloced_cpu_masks;
}
for(i = 0; i < num_domains; ++i) {
if(!zalloc_cpumask_var(&m->domain_to_cpus[i].mask, GFP_ATOMIC))
goto failure;
++num_alloced_domain_masks;
}
return 0;
failure:
for(i = 0; i < num_alloced_cpu_masks; ++i)
free_cpumask_var(m->cpu_to_domains[i].mask);
for(i = 0; i < num_alloced_domain_masks; ++i)
free_cpumask_var(m->domain_to_cpus[i].mask);
if(m->cpu_to_domains)
kfree(m->cpu_to_domains);
if(m->domain_to_cpus)
kfree(m->domain_to_cpus);
return -ENOMEM;
}
static int __init irq_affinity_setup(char *str)
{
zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
cpulist_parse(str, irq_default_affinity);
/*
* Set at least the boot cpu. We don't want to end up with
* bugreports caused by random comandline masks
*/
cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
return 1;
}
static int mem_rx_setup(struct link_device *ld)
{
struct mem_link_device *mld = to_mem_link_device(ld);
if (!zalloc_cpumask_var(&mld->dmask, GFP_KERNEL))
return -ENOMEM;
if (!zalloc_cpumask_var(&mld->imask, GFP_KERNEL))
return -ENOMEM;
if (!zalloc_cpumask_var(&mld->tmask, GFP_KERNEL))
return -ENOMEM;
#ifdef CONFIG_ARGOS
/* Below hard-coded mask values should be removed later on.
* Like net-sysfs, argos module also should support sysfs knob,
* so that user layer must be able to control these cpu mask. */
#ifdef CONFIG_SCHED_HMP
cpumask_copy(mld->dmask, &hmp_slow_cpu_mask);
#endif
cpumask_or(mld->imask, mld->imask, cpumask_of(3));
argos_irq_affinity_setup_label(217, "IPC", mld->imask, mld->dmask);
#endif
ld->tx_wq = create_singlethread_workqueue("mem_tx_work");
if (!ld->tx_wq) {
mif_err("%s: ERR! fail to create tx_wq\n", ld->name);
return -ENOMEM;
}
ld->rx_wq = alloc_workqueue(
"mem_rx_work", WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
if (!ld->rx_wq) {
mif_err("%s: ERR! fail to create rx_wq\n", ld->name);
return -ENOMEM;
}
INIT_DELAYED_WORK(&ld->rx_delayed_work, link_to_demux_work);
return 0;
}
static int init_rootdomain(struct root_domain *rd)
{
if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
goto out;
if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_dlo_mask;
#ifdef HAVE_RT_PUSH_IPI
rd->rto_cpu = -1;
raw_spin_lock_init(&rd->rto_lock);
init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
#endif
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
goto free_rto_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_cpudl;
return 0;
free_cpudl:
cpudl_cleanup(&rd->cpudl);
free_rto_mask:
free_cpumask_var(rd->rto_mask);
free_dlo_mask:
free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
free_cpumask_var(rd->span);
out:
return -ENOMEM;
}
static struct p2m_domain *p2m_init_one(struct domain *d)
{
struct p2m_domain *p2m = xzalloc(struct p2m_domain);
if ( !p2m )
return NULL;
if ( !zalloc_cpumask_var(&p2m->dirty_cpumask) )
goto free_p2m;
if ( p2m_initialise(d, p2m) )
goto free_cpumask;
return p2m;
free_cpumask:
free_cpumask_var(p2m->dirty_cpumask);
free_p2m:
xfree(p2m);
return NULL;
}
static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf)
{
struct rps_map *map;
cpumask_var_t mask;
int i, len;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
rcu_read_lock();
map = rcu_dereference(queue->rps_map);
if (map)
for (i = 0; i < map->len; i++)
cpumask_set_cpu(map->cpus[i], mask);
len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
rcu_read_unlock();
free_cpumask_var(mask);
return len < PAGE_SIZE ? len : -EINVAL;
}
int get_cluster_size(enum cache_level level)
{
cpumask_var_t mask;
int ok;
int num_cpus;
if (level == GLOBAL_CLUSTER)
return num_online_cpus();
else {
if (!zalloc_cpumask_var(&mask, GFP_ATOMIC))
return -ENOMEM;
/* assumes CPU 0 is representative of all CPUs */
ok = get_shared_cpu_map(mask, 0, level);
/* ok == 0 means we got the map; otherwise it's an invalid cache level */
if (ok == 0)
num_cpus = cpumask_weight(mask);
free_cpumask_var(mask);
if (ok == 0)
return num_cpus;
else
return -EINVAL;
}
}
/*
* cpudl_init - initialize the cpudl structure
* @cp: the cpudl max-heap context
*/
int cpudl_init(struct cpudl *cp)
{
int i;
memset(cp, 0, sizeof(*cp));
raw_spin_lock_init(&cp->lock);
cp->size = 0;
cp->elements = kcalloc(nr_cpu_ids,
sizeof(struct cpudl_item),
GFP_KERNEL);
if (!cp->elements)
return -ENOMEM;
if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
kfree(cp->elements);
return -ENOMEM;
}
for_each_possible_cpu(i)
cp->elements[i].idx = IDX_INVALID;
return 0;
}
static int acpi_processor_add(struct acpi_device *device)
{
struct acpi_processor *pr = NULL;
if (!device)
return -EINVAL;
pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
if (!pr)
return -ENOMEM;
if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
kfree(pr);
return -ENOMEM;
}
pr->handle = device->handle;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
return 0;
}
void __init init_amd_e400_c1e_mask(void)
{
/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
if (x86_idle == amd_e400_idle)
zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
}
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;
}
struct domain *domain_create(
domid_t domid, unsigned int domcr_flags, uint32_t ssidref)
{
struct domain *d, **pd;
enum { INIT_xsm = 1u<<0, INIT_watchdog = 1u<<1, INIT_rangeset = 1u<<2,
INIT_evtchn = 1u<<3, INIT_gnttab = 1u<<4, INIT_arch = 1u<<5 };
int err, init_status = 0;
int poolid = CPUPOOLID_NONE;
if ( (d = alloc_domain_struct()) == NULL )
return ERR_PTR(-ENOMEM);
d->domain_id = domid;
lock_profile_register_struct(LOCKPROF_TYPE_PERDOM, d, domid, "Domain");
if ( (err = xsm_alloc_security_domain(d)) != 0 )
goto fail;
init_status |= INIT_xsm;
watchdog_domain_init(d);
init_status |= INIT_watchdog;
atomic_set(&d->refcnt, 1);
spin_lock_init_prof(d, domain_lock);
spin_lock_init_prof(d, page_alloc_lock);
spin_lock_init(&d->hypercall_deadlock_mutex);
INIT_PAGE_LIST_HEAD(&d->page_list);
INIT_PAGE_LIST_HEAD(&d->xenpage_list);
spin_lock_init(&d->node_affinity_lock);
d->node_affinity = NODE_MASK_ALL;
d->auto_node_affinity = 1;
spin_lock_init(&d->shutdown_lock);
d->shutdown_code = -1;
err = -ENOMEM;
if ( !zalloc_cpumask_var(&d->domain_dirty_cpumask) )
goto fail;
if ( domcr_flags & DOMCRF_hvm )
d->is_hvm = 1;
if ( domid == 0 )
{
d->is_pinned = opt_dom0_vcpus_pin;
d->disable_migrate = 1;
}
rangeset_domain_initialise(d);
init_status |= INIT_rangeset;
d->iomem_caps = rangeset_new(d, "I/O Memory", RANGESETF_prettyprint_hex);
d->irq_caps = rangeset_new(d, "Interrupts", 0);
if ( (d->iomem_caps == NULL) || (d->irq_caps == NULL) )
goto fail;
if ( domcr_flags & DOMCRF_dummy )
return d;
if ( !is_idle_domain(d) )
{
if ( (err = xsm_domain_create(XSM_HOOK, d, ssidref)) != 0 )
goto fail;
d->is_paused_by_controller = 1;
atomic_inc(&d->pause_count);
if ( domid )
d->nr_pirqs = nr_static_irqs + extra_domU_irqs;
else
d->nr_pirqs = nr_static_irqs + extra_dom0_irqs;
if ( d->nr_pirqs > nr_irqs )
d->nr_pirqs = nr_irqs;
radix_tree_init(&d->pirq_tree);
if ( (err = evtchn_init(d)) != 0 )
goto fail;
init_status |= INIT_evtchn;
if ( (err = grant_table_create(d)) != 0 )
goto fail;
init_status |= INIT_gnttab;
poolid = 0;
err = -ENOMEM;
d->mem_event = xzalloc(struct mem_event_per_domain);
if ( !d->mem_event )
goto fail;
}
if ( (err = arch_domain_create(d, domcr_flags)) != 0 )
goto fail;
init_status |= INIT_arch;
if ( (err = cpupool_add_domain(d, poolid)) != 0 )
goto fail;
if ( (err = sched_init_domain(d)) != 0 )
goto fail;
if ( !is_idle_domain(d) )
{
spin_lock(&domlist_update_lock);
pd = &domain_list; /* NB. domain_list maintained in order of domid. */
for ( pd = &domain_list; *pd != NULL; pd = &(*pd)->next_in_list )
if ( (*pd)->domain_id > d->domain_id )
break;
d->next_in_list = *pd;
d->next_in_hashbucket = domain_hash[DOMAIN_HASH(domid)];
rcu_assign_pointer(*pd, d);
rcu_assign_pointer(domain_hash[DOMAIN_HASH(domid)], d);
spin_unlock(&domlist_update_lock);
}
return d;
fail:
d->is_dying = DOMDYING_dead;
atomic_set(&d->refcnt, DOMAIN_DESTROYED);
xfree(d->mem_event);
if ( init_status & INIT_arch )
arch_domain_destroy(d);
if ( init_status & INIT_gnttab )
grant_table_destroy(d);
if ( init_status & INIT_evtchn )
{
evtchn_destroy(d);
evtchn_destroy_final(d);
radix_tree_destroy(&d->pirq_tree, free_pirq_struct);
}
if ( init_status & INIT_rangeset )
rangeset_domain_destroy(d);
if ( init_status & INIT_watchdog )
watchdog_domain_destroy(d);
if ( init_status & INIT_xsm )
xsm_free_security_domain(d);
free_cpumask_var(d->domain_dirty_cpumask);
free_domain_struct(d);
return ERR_PTR(err);
}
struct vcpu *alloc_vcpu(
struct domain *d, unsigned int vcpu_id, unsigned int cpu_id)
{
struct vcpu *v;
BUG_ON((!is_idle_domain(d) || vcpu_id) && d->vcpu[vcpu_id]);
if ( (v = alloc_vcpu_struct()) == NULL )
return NULL;
v->domain = d;
v->vcpu_id = vcpu_id;
spin_lock_init(&v->virq_lock);
tasklet_init(&v->continue_hypercall_tasklet, NULL, 0);
if ( !zalloc_cpumask_var(&v->cpu_affinity) ||
!zalloc_cpumask_var(&v->cpu_affinity_tmp) ||
!zalloc_cpumask_var(&v->cpu_affinity_saved) ||
!zalloc_cpumask_var(&v->vcpu_dirty_cpumask) )
goto fail_free;
if ( is_idle_domain(d) )
{
v->runstate.state = RUNSTATE_running;
}
else
{
v->runstate.state = RUNSTATE_offline;
v->runstate.state_entry_time = NOW();
set_bit(_VPF_down, &v->pause_flags);
v->vcpu_info = ((vcpu_id < XEN_LEGACY_MAX_VCPUS)
? (vcpu_info_t *)&shared_info(d, vcpu_info[vcpu_id])
: &dummy_vcpu_info);
v->vcpu_info_mfn = INVALID_MFN;
init_waitqueue_vcpu(v);
}
if ( sched_init_vcpu(v, cpu_id) != 0 )
goto fail_wq;
if ( vcpu_initialise(v) != 0 )
{
sched_destroy_vcpu(v);
fail_wq:
destroy_waitqueue_vcpu(v);
fail_free:
free_cpumask_var(v->cpu_affinity);
free_cpumask_var(v->cpu_affinity_tmp);
free_cpumask_var(v->cpu_affinity_saved);
free_cpumask_var(v->vcpu_dirty_cpumask);
free_vcpu_struct(v);
return NULL;
}
d->vcpu[vcpu_id] = v;
if ( vcpu_id != 0 )
{
int prev_id = v->vcpu_id - 1;
while ( (prev_id >= 0) && (d->vcpu[prev_id] == NULL) )
prev_id--;
BUG_ON(prev_id < 0);
v->next_in_list = d->vcpu[prev_id]->next_in_list;
d->vcpu[prev_id]->next_in_list = v;
}
/* Must be called after making new vcpu visible to for_each_vcpu(). */
vcpu_check_shutdown(v);
domain_update_node_affinity(d);
return v;
}
int assign_cpus_to_clusters(enum cache_level level,
struct scheduling_cluster* clusters[],
unsigned int num_clusters,
struct cluster_cpu* cpus[],
unsigned int num_cpus)
{
cpumask_var_t mask;
unsigned int i, free_cluster = 0, low_cpu;
int err = 0;
if (!zalloc_cpumask_var(&mask, GFP_ATOMIC))
return -ENOMEM;
/* clear cluster pointers */
for (i = 0; i < num_cpus; i++) {
cpus[i]->id = i;
cpus[i]->cluster = NULL;
}
/* initialize clusters */
for (i = 0; i < num_clusters; i++) {
clusters[i]->id = i;
INIT_LIST_HEAD(&clusters[i]->cpus);
}
/* Assign each CPU. Two assumtions are made:
* 1) The index of a cpu in cpus corresponds to its processor id (i.e., the index in a cpu mask).
* 2) All cpus that belong to some cluster are online.
*/
for_each_online_cpu(i) {
/* get lowest-id CPU in cluster */
if (level != GLOBAL_CLUSTER) {
err = get_shared_cpu_map(mask, cpus[i]->id, level);
if (err != 0) {
/* ugh... wrong cache level? Either caller screwed up
* or the CPU topology is weird. */
printk(KERN_ERR "Could not set up clusters for L%d sharing (max: L%d).\n",
level, err);
err = -EINVAL;
goto out;
}
low_cpu = cpumask_first(mask);
} else
low_cpu = 0;
if (low_cpu == i) {
/* caller must provide an appropriate number of clusters */
BUG_ON(free_cluster >= num_clusters);
/* create new cluster */
cpus[i]->cluster = clusters[free_cluster++];
} else {
/* low_cpu points to the right cluster
* Assumption: low_cpu is actually online and was processed earlier. */
cpus[i]->cluster = cpus[low_cpu]->cluster;
}
/* enqueue in cpus list */
list_add_tail(&cpus[i]->cluster_list, &cpus[i]->cluster->cpus);
printk(KERN_INFO "Assigning CPU%u to cluster %u\n.", i, cpus[i]->cluster->id);
}
out:
free_cpumask_var(mask);
return err;
}
/**
* channel_backend_init - initialize a channel backend
* @chanb: channel backend
* @name: channel name
* @config: client ring buffer configuration
* @priv: client private data
* @parent: dentry of parent directory, %NULL for root directory
* @subbuf_size: size of sub-buffers (> PAGE_SIZE, power of 2)
* @num_subbuf: number of sub-buffers (power of 2)
*
* Returns channel pointer if successful, %NULL otherwise.
*
* Creates per-cpu channel buffers using the sizes and attributes
* specified. The created channel buffer files will be named
* name_0...name_N-1. File permissions will be %S_IRUSR.
*
* Called with CPU hotplug disabled.
*/
int channel_backend_init(struct channel_backend *chanb,
const char *name,
const struct lib_ring_buffer_config *config,
void *priv, size_t subbuf_size, size_t num_subbuf)
{
struct channel *chan = container_of(chanb, struct channel, backend);
unsigned int i;
int ret;
if (!name)
return -EPERM;
/* Check that the subbuffer size is larger than a page. */
if (subbuf_size < PAGE_SIZE)
return -EINVAL;
/*
* Make sure the number of subbuffers and subbuffer size are
* power of 2 and nonzero.
*/
if (!subbuf_size || (subbuf_size & (subbuf_size - 1)))
return -EINVAL;
if (!num_subbuf || (num_subbuf & (num_subbuf - 1)))
return -EINVAL;
/*
* Overwrite mode buffers require at least 2 subbuffers per
* buffer.
*/
if (config->mode == RING_BUFFER_OVERWRITE && num_subbuf < 2)
return -EINVAL;
ret = subbuffer_id_check_index(config, num_subbuf);
if (ret)
return ret;
chanb->priv = priv;
chanb->buf_size = num_subbuf * subbuf_size;
chanb->subbuf_size = subbuf_size;
chanb->buf_size_order = get_count_order(chanb->buf_size);
chanb->subbuf_size_order = get_count_order(subbuf_size);
chanb->num_subbuf_order = get_count_order(num_subbuf);
chanb->extra_reader_sb =
(config->mode == RING_BUFFER_OVERWRITE) ? 1 : 0;
chanb->num_subbuf = num_subbuf;
strlcpy(chanb->name, name, NAME_MAX);
memcpy(&chanb->config, config, sizeof(chanb->config));
if (config->alloc == RING_BUFFER_ALLOC_PER_CPU) {
if (!zalloc_cpumask_var(&chanb->cpumask, GFP_KERNEL))
return -ENOMEM;
}
if (config->alloc == RING_BUFFER_ALLOC_PER_CPU) {
/* Allocating the buffer per-cpu structures */
chanb->buf = alloc_percpu(struct lib_ring_buffer);
if (!chanb->buf)
goto free_cpumask;
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,10,0))
chanb->cpuhp_prepare.component = LTTNG_RING_BUFFER_BACKEND;
ret = cpuhp_state_add_instance(lttng_rb_hp_prepare,
&chanb->cpuhp_prepare.node);
if (ret)
goto free_bufs;
#else /* #if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,10,0)) */
{
/*
* In case of non-hotplug cpu, if the ring-buffer is allocated
* in early initcall, it will not be notified of secondary cpus.
* In that off case, we need to allocate for all possible cpus.
*/
#ifdef CONFIG_HOTPLUG_CPU
/*
* buf->backend.allocated test takes care of concurrent CPU
* hotplug.
* Priority higher than frontend, so we create the ring buffer
* before we start the timer.
*/
chanb->cpu_hp_notifier.notifier_call =
lib_ring_buffer_cpu_hp_callback;
chanb->cpu_hp_notifier.priority = 5;
register_hotcpu_notifier(&chanb->cpu_hp_notifier);
get_online_cpus();
for_each_online_cpu(i) {
ret = lib_ring_buffer_create(per_cpu_ptr(chanb->buf, i),
chanb, i);
if (ret)
goto free_bufs; /* cpu hotplug locked */
}
put_online_cpus();
#else
for_each_possible_cpu(i) {
ret = lib_ring_buffer_create(per_cpu_ptr(chanb->buf, i),
chanb, i);
if (ret)
goto free_bufs;
}
#endif
}
#endif /* #else #if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,10,0)) */
} else {
/*
* Do not put anything in here which needs the core to be online.
* For example MSR access or setting up things which check for cpuinfo_x86
* (cpu_data(cpu)) values, like CPU feature flags, family, model, etc.
* Such things have to be put in and set up above in acpi_processor_start()
*/
static int __cpuinit acpi_processor_add(struct acpi_device *device)
{
struct acpi_processor *pr = NULL;
int result = 0;
struct device *dev;
pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
if (!pr)
return -ENOMEM;
if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
result = -ENOMEM;
goto err_free_pr;
}
pr->handle = device->handle;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
result = acpi_processor_get_info(device);
if (result) {
/* Processor is physically not present */
return 0;
}
#ifdef CONFIG_SMP
if (pr->id >= setup_max_cpus && pr->id != 0)
return 0;
#endif
BUG_ON((pr->id >= nr_cpu_ids) || (pr->id < 0));
/*
* Buggy BIOS check
* ACPI id of processors can be reported wrongly by the BIOS.
* Don't trust it blindly
*/
if (per_cpu(processor_device_array, pr->id) != NULL &&
per_cpu(processor_device_array, pr->id) != device) {
printk(KERN_WARNING "BIOS reported wrong ACPI id "
"for the processor\n");
result = -ENODEV;
goto err_free_cpumask;
}
per_cpu(processor_device_array, pr->id) = device;
per_cpu(processors, pr->id) = pr;
dev = get_cpu_device(pr->id);
if (sysfs_create_link(&device->dev.kobj, &dev->kobj, "sysdev")) {
result = -EFAULT;
goto err_clear_processor;
}
/*
* Do not start hotplugged CPUs now, but when they
* are onlined the first time
*/
if (pr->flags.need_hotplug_init)
return 0;
result = acpi_processor_start(pr);
if (result)
goto err_remove_sysfs;
return 0;
err_remove_sysfs:
sysfs_remove_link(&device->dev.kobj, "sysdev");
err_clear_processor:
/*
* processor_device_array is not cleared to allow checks for buggy BIOS
*/
per_cpu(processors, pr->id) = NULL;
err_free_cpumask:
free_cpumask_var(pr->throttling.shared_cpu_map);
err_free_pr:
kfree(pr);
return result;
}
static int __cpuinit acpi_processor_add(struct acpi_device *device)
{
struct acpi_processor *pr = NULL;
int result = 0;
struct sys_device *sysdev;
pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
if (!pr)
return -ENOMEM;
if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
kfree(pr);
return -ENOMEM;
}
pr->handle = device->handle;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
processor_extcntl_init();
result = acpi_processor_get_info(device);
if (result ||
((pr->id == -1) && !processor_cntl_external())) {
/* Processor is physically not present */
return 0;
}
BUG_ON(!processor_cntl_external() &&
((pr->id >= nr_cpu_ids) || (pr->id < 0)));
/*
* Buggy BIOS check
* ACPI id of processors can be reported wrongly by the BIOS.
* Don't trust it blindly
*/
#ifndef CONFIG_XEN
if (per_cpu(processor_device_array, pr->id) != NULL &&
per_cpu(processor_device_array, pr->id) != device) {
#else
BUG_ON(pr->acpi_id >= NR_ACPI_CPUS);
if (processor_device_array[pr->acpi_id] != NULL &&
processor_device_array[pr->acpi_id] != device) {
#endif
printk(KERN_WARNING "BIOS reported wrong ACPI id "
"for the processor\n");
result = -ENODEV;
goto err_free_cpumask;
}
#ifndef CONFIG_XEN
per_cpu(processor_device_array, pr->id) = device;
per_cpu(processors, pr->id) = pr;
#else
processor_device_array[pr->acpi_id] = device;
if (pr->id != -1)
per_cpu(processors, pr->id) = pr;
#endif
result = acpi_processor_add_fs(device);
if (result)
goto err_free_cpumask;
if (pr->id != -1) {
sysdev = get_cpu_sysdev(pr->id);
if (sysfs_create_link(&device->dev.kobj, &sysdev->kobj, "sysdev")) {
result = -EFAULT;
goto err_remove_fs;
}
}
/* _PDC call should be done before doing anything else (if reqd.). */
arch_acpi_processor_init_pdc(pr);
acpi_processor_set_pdc(pr);
arch_acpi_processor_cleanup_pdc(pr);
#if defined(CONFIG_CPU_FREQ) || defined(CONFIG_PROCESSOR_EXTERNAL_CONTROL)
acpi_processor_ppc_has_changed(pr);
#endif
/*
* pr->id may equal to -1 while processor_cntl_external enabled.
* throttle and thermal module don't support this case.
* Tx only works when dom0 vcpu == pcpu num by far, as we give
* control to dom0.
*/
if (pr->id != -1) {
acpi_processor_get_throttling_info(pr);
acpi_processor_get_limit_info(pr);
}
acpi_processor_power_init(pr, device);
result = processor_extcntl_prepare(pr);
if (result)
goto err_power_exit;
pr->cdev = thermal_cooling_device_register("Processor", device,
&processor_cooling_ops);
if (IS_ERR(pr->cdev)) {
result = PTR_ERR(pr->cdev);
goto err_power_exit;
}
dev_info(&device->dev, "registered as cooling_device%d\n",
pr->cdev->id);
result = sysfs_create_link(&device->dev.kobj,
&pr->cdev->device.kobj,
"thermal_cooling");
if (result) {
printk(KERN_ERR PREFIX "Create sysfs link\n");
goto err_thermal_unregister;
}
result = sysfs_create_link(&pr->cdev->device.kobj,
&device->dev.kobj,
"device");
if (result) {
printk(KERN_ERR PREFIX "Create sysfs link\n");
goto err_remove_sysfs;
}
return 0;
err_remove_sysfs:
sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
err_thermal_unregister:
thermal_cooling_device_unregister(pr->cdev);
err_power_exit:
acpi_processor_power_exit(pr, device);
err_remove_fs:
acpi_processor_remove_fs(device);
err_free_cpumask:
free_cpumask_var(pr->throttling.shared_cpu_map);
return result;
}
static int acpi_processor_remove(struct acpi_device *device, int type)
{
struct acpi_processor *pr = NULL;
if (!device || !acpi_driver_data(device))
return -EINVAL;
pr = acpi_driver_data(device);
if (!processor_cntl_external() && pr->id >= nr_cpu_ids)
goto free;
if (type == ACPI_BUS_REMOVAL_EJECT) {
if (acpi_processor_handle_eject(pr))
return -EINVAL;
}
acpi_processor_power_exit(pr, device);
if (pr->id != -1)
sysfs_remove_link(&device->dev.kobj, "sysdev");
acpi_processor_remove_fs(device);
if (pr->cdev) {
sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
sysfs_remove_link(&pr->cdev->device.kobj, "device");
thermal_cooling_device_unregister(pr->cdev);
pr->cdev = NULL;
}
#ifndef CONFIG_XEN
per_cpu(processors, pr->id) = NULL;
per_cpu(processor_device_array, pr->id) = NULL;
#else
if (pr->id != -1)
per_cpu(processors, pr->id) = NULL;
processor_device_array[pr->acpi_id] = NULL;
#endif
free:
free_cpumask_var(pr->throttling.shared_cpu_map);
kfree(pr);
return 0;
}
#ifdef CONFIG_ACPI_HOTPLUG_CPU
/****************************************************************************
* Acpi processor hotplug support *
****************************************************************************/
static int is_processor_present(acpi_handle handle)
{
acpi_status status;
unsigned long long sta = 0;
status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_PRESENT))
return 1;
/*
* _STA is mandatory for a processor that supports hot plug
*/
if (status == AE_NOT_FOUND)
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"Processor does not support hot plug\n"));
else
ACPI_EXCEPTION((AE_INFO, status,
"Processor Device is not present"));
return 0;
}
static int __cpuinit acpi_processor_add(struct acpi_device *device)
{
struct acpi_processor *pr = NULL;
int result = 0;
struct sys_device *sysdev;
pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
if (!pr)
return -ENOMEM;
if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
kfree(pr);
return -ENOMEM;
}
pr->handle = device->handle;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
result = acpi_processor_get_info(device);
if (result) {
/* Processor is physically not present */
return 0;
}
BUG_ON((pr->id >= nr_cpu_ids) || (pr->id < 0));
/*
* Buggy BIOS check
* ACPI id of processors can be reported wrongly by the BIOS.
* Don't trust it blindly
*/
if (per_cpu(processor_device_array, pr->id) != NULL &&
per_cpu(processor_device_array, pr->id) != device) {
printk(KERN_WARNING "BIOS reported wrong ACPI id "
"for the processor\n");
result = -ENODEV;
goto err_free_cpumask;
}
per_cpu(processor_device_array, pr->id) = device;
per_cpu(processors, pr->id) = pr;
result = acpi_processor_add_fs(device);
if (result)
goto err_free_cpumask;
sysdev = get_cpu_sysdev(pr->id);
if (sysfs_create_link(&device->dev.kobj, &sysdev->kobj, "sysdev")) {
result = -EFAULT;
goto err_remove_fs;
}
/* _PDC call should be done before doing anything else (if reqd.). */
arch_acpi_processor_init_pdc(pr);
acpi_processor_set_pdc(pr);
arch_acpi_processor_cleanup_pdc(pr);
#ifdef CONFIG_CPU_FREQ
acpi_processor_ppc_has_changed(pr);
#endif
acpi_processor_get_throttling_info(pr);
acpi_processor_get_limit_info(pr);
acpi_processor_power_init(pr, device);
pr->cdev = thermal_cooling_device_register("Processor", device,
&processor_cooling_ops);
if (IS_ERR(pr->cdev)) {
result = PTR_ERR(pr->cdev);
goto err_power_exit;
}
dev_info(&device->dev, "registered as cooling_device%d\n",
pr->cdev->id);
result = sysfs_create_link(&device->dev.kobj,
&pr->cdev->device.kobj,
"thermal_cooling");
if (result) {
printk(KERN_ERR PREFIX "Create sysfs link\n");
goto err_thermal_unregister;
}
result = sysfs_create_link(&pr->cdev->device.kobj,
&device->dev.kobj,
"device");
if (result) {
printk(KERN_ERR PREFIX "Create sysfs link\n");
goto err_remove_sysfs;
}
return 0;
err_remove_sysfs:
sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
err_thermal_unregister:
thermal_cooling_device_unregister(pr->cdev);
err_power_exit:
acpi_processor_power_exit(pr, device);
err_remove_fs:
acpi_processor_remove_fs(device);
err_free_cpumask:
free_cpumask_var(pr->throttling.shared_cpu_map);
return result;
}
static int acpi_processor_add(struct acpi_device *device,
const struct acpi_device_id *id)
{
struct acpi_processor *pr;
struct device *dev;
int result = 0;
pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
if (!pr)
return -ENOMEM;
if (!zalloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
result = -ENOMEM;
goto err_free_pr;
}
pr->handle = device->handle;
strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
result = acpi_processor_get_info(device);
if (result) /* Processor is not physically present or unavailable */
return 0;
#ifdef CONFIG_SMP
if (pr->id >= setup_max_cpus && pr->id != 0)
return 0;
#endif
BUG_ON(pr->id >= nr_cpu_ids);
/*
* Buggy BIOS check.
* ACPI id of processors can be reported wrongly by the BIOS.
* Don't trust it blindly
*/
if (per_cpu(processor_device_array, pr->id) != NULL &&
per_cpu(processor_device_array, pr->id) != device) {
dev_warn(&device->dev,
"BIOS reported wrong ACPI id %d for the processor\n",
pr->id);
/* Give up, but do not abort the namespace scan. */
goto err;
}
/*
* processor_device_array is not cleared on errors to allow buggy BIOS
* checks.
*/
per_cpu(processor_device_array, pr->id) = device;
per_cpu(processors, pr->id) = pr;
dev = get_cpu_device(pr->id);
if (!dev) {
result = -ENODEV;
goto err;
}
result = acpi_bind_one(dev, pr->handle);
if (result)
goto err;
pr->dev = dev;
dev->offline = pr->flags.need_hotplug_init;
/* Trigger the processor driver's .probe() if present. */
if (device_attach(dev) >= 0)
return 1;
dev_err(dev, "Processor driver could not be attached\n");
acpi_unbind_one(dev);
err:
free_cpumask_var(pr->throttling.shared_cpu_map);
device->driver_data = NULL;
per_cpu(processors, pr->id) = NULL;
err_free_pr:
kfree(pr);
return result;
}
/**
* acpi_get_psd_map - Map the CPUs in a common freq domain.
* @all_cpu_data: Ptrs to CPU specific CPPC data including PSD info.
*
* Return: 0 for success or negative value for err.
*/
int acpi_get_psd_map(struct cpudata **all_cpu_data)
{
int count_target;
int retval = 0;
unsigned int i, j;
cpumask_var_t covered_cpus;
struct cpudata *pr, *match_pr;
struct acpi_psd_package *pdomain;
struct acpi_psd_package *match_pdomain;
struct cpc_desc *cpc_ptr, *match_cpc_ptr;
if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
return -ENOMEM;
/*
* Now that we have _PSD data from all CPUs, lets setup P-state
* domain info.
*/
for_each_possible_cpu(i) {
pr = all_cpu_data[i];
if (!pr)
continue;
if (cpumask_test_cpu(i, covered_cpus))
continue;
cpc_ptr = per_cpu(cpc_desc_ptr, i);
if (!cpc_ptr) {
retval = -EFAULT;
goto err_ret;
}
pdomain = &(cpc_ptr->domain_info);
cpumask_set_cpu(i, pr->shared_cpu_map);
cpumask_set_cpu(i, covered_cpus);
if (pdomain->num_processors <= 1)
continue;
/* Validate the Domain info */
count_target = pdomain->num_processors;
if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;
for_each_possible_cpu(j) {
if (i == j)
continue;
match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
if (!match_cpc_ptr) {
retval = -EFAULT;
goto err_ret;
}
match_pdomain = &(match_cpc_ptr->domain_info);
if (match_pdomain->domain != pdomain->domain)
continue;
/* Here i and j are in the same domain */
if (match_pdomain->num_processors != count_target) {
retval = -EFAULT;
goto err_ret;
}
if (pdomain->coord_type != match_pdomain->coord_type) {
retval = -EFAULT;
goto err_ret;
}
cpumask_set_cpu(j, covered_cpus);
cpumask_set_cpu(j, pr->shared_cpu_map);
}
for_each_possible_cpu(j) {
if (i == j)
continue;
match_pr = all_cpu_data[j];
if (!match_pr)
continue;
match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
if (!match_cpc_ptr) {
retval = -EFAULT;
goto err_ret;
}
match_pdomain = &(match_cpc_ptr->domain_info);
if (match_pdomain->domain != pdomain->domain)
continue;
match_pr->shared_type = pr->shared_type;
cpumask_copy(match_pr->shared_cpu_map,
pr->shared_cpu_map);
}
}
err_ret:
for_each_possible_cpu(i) {
pr = all_cpu_data[i];
if (!pr)
continue;
/* Assume no coordination on any error parsing domain info */
if (retval) {
cpumask_clear(pr->shared_cpu_map);
cpumask_set_cpu(i, pr->shared_cpu_map);
pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
}
}
free_cpumask_var(covered_cpus);
return retval;
}
