int cpu = smp_processor_id();
previous_current = curr_task(cpu);
- set_curr_task(cpu, current);
+ ia64_set_curr_task(cpu, current);
if ((p = strchr(current->comm, ' ')))
*p = '\0';
cpumask_clear_cpu(i, &mca_cpu); /* wake next cpu */
while (monarch_cpu != -1)
cpu_relax(); /* spin until last cpu leaves */
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu]
= IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
return;
}
}
}
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
monarch_cpu = -1; /* This frees the slaves and previous monarchs */
}
NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1);
mprintk("Slave on cpu %d returning to normal service.\n", cpu);
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
atomic_dec(&slaves);
return;
mprintk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu);
atomic_dec(&monarchs);
- set_curr_task(cpu, previous_current);
+ ia64_set_curr_task(cpu, previous_current);
monarch_cpu = -1;
return;
}
PAGE_KERNEL)));
}
- static void ia64_mca_cmc_vector_adjust(void *dummy)
+ static int ia64_mca_cpu_online(unsigned int cpu)
{
unsigned long flags;
if (!cmc_polling_enabled)
ia64_mca_cmc_vector_enable(NULL);
local_irq_restore(flags);
+ return 0;
}
- static int mca_cpu_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
- {
- switch (action) {
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- ia64_mca_cmc_vector_adjust(NULL);
- break;
- }
- return NOTIFY_OK;
- }
-
- static struct notifier_block mca_cpu_notifier = {
- .notifier_call = mca_cpu_callback
- };
-
/*
* ia64_mca_init
*
if (!mca_init)
return 0;
- register_hotcpu_notifier(&mca_cpu_notifier);
-
/* Setup the CMCI/P vector and handler */
setup_timer(&cmc_poll_timer, ia64_mca_cmc_poll, 0UL);
/* Unmask/enable the vector */
cmc_polling_enabled = 0;
- schedule_work(&cmc_enable_work);
-
+ cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "ia64/mca:online",
+ ia64_mca_cpu_online, NULL);
IA64_MCA_DEBUG("%s: CMCI/P setup and enabled.\n", __func__);
#ifdef CONFIG_ACPI
static unsigned long set_apic_id(unsigned int id)
{
- unsigned long x;
-
- /* maskout x2apic_extra_bits ? */
- x = id;
- return x;
+ /* CHECKME: Do we need to mask out the xapic extra bits? */
+ return id;
}
static unsigned int uv_read_apic_id(void)
return apic == &apic_x2apic_uv_x;
}
-static struct apic __refdata apic_x2apic_uv_x = {
+static struct apic apic_x2apic_uv_x __ro_after_init = {
.name = "UV large system",
.probe = uv_probe,
mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
}
- static void uv_heartbeat_enable(int cpu)
+ static int uv_heartbeat_enable(unsigned int cpu)
{
while (!uv_cpu_scir_info(cpu)->enabled) {
struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer;
/* also ensure that boot cpu is enabled */
cpu = 0;
}
+ return 0;
}
#ifdef CONFIG_HOTPLUG_CPU
- static void uv_heartbeat_disable(int cpu)
+ static int uv_heartbeat_disable(unsigned int cpu)
{
if (uv_cpu_scir_info(cpu)->enabled) {
uv_cpu_scir_info(cpu)->enabled = 0;
del_timer(&uv_cpu_scir_info(cpu)->timer);
}
uv_set_cpu_scir_bits(cpu, 0xff);
- }
-
- /*
- * cpu hotplug notifier
- */
- static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
- {
- long cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DOWN_FAILED:
- case CPU_ONLINE:
- uv_heartbeat_enable(cpu);
- break;
- case CPU_DOWN_PREPARE:
- uv_heartbeat_disable(cpu);
- break;
- default:
- break;
- }
- return NOTIFY_OK;
+ return 0;
}
static __init void uv_scir_register_cpu_notifier(void)
{
- hotcpu_notifier(uv_scir_cpu_notify, 0);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/x2apic-uvx:online",
+ uv_heartbeat_enable, uv_heartbeat_disable);
}
#else /* !CONFIG_HOTPLUG_CPU */
kvm_spinlock_init();
}
- static void kvm_guest_cpu_online(void *dummy)
- {
- kvm_guest_cpu_init();
- }
-
- static void kvm_guest_cpu_offline(void *dummy)
+ static void kvm_guest_cpu_offline(void)
{
kvm_disable_steal_time();
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apf_task_wake_all();
}
- static int kvm_cpu_notify(struct notifier_block *self, unsigned long action,
- void *hcpu)
+ static int kvm_cpu_online(unsigned int cpu)
{
- int cpu = (unsigned long)hcpu;
- switch (action) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- case CPU_ONLINE_FROZEN:
- smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0);
- break;
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1);
- break;
- default:
- break;
- }
- return NOTIFY_OK;
+ local_irq_disable();
+ kvm_guest_cpu_init();
+ local_irq_enable();
+ return 0;
}
- static struct notifier_block kvm_cpu_notifier = {
- .notifier_call = kvm_cpu_notify,
- };
+ static int kvm_cpu_down_prepare(unsigned int cpu)
+ {
+ local_irq_disable();
+ kvm_guest_cpu_offline();
+ local_irq_enable();
+ return 0;
+ }
#endif
static void __init kvm_apf_trap_init(void)
#ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
- register_cpu_notifier(&kvm_cpu_notifier);
+ if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
+ kvm_cpu_online, kvm_cpu_down_prepare) < 0)
+ pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
#else
kvm_guest_cpu_init();
#endif
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
}
-
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
#include <asm/qspinlock.h>
static void kvm_wait(u8 *ptr, u8 val)
local_irq_restore(flags);
}
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-
-enum kvm_contention_stat {
- TAKEN_SLOW,
- TAKEN_SLOW_PICKUP,
- RELEASED_SLOW,
- RELEASED_SLOW_KICKED,
- NR_CONTENTION_STATS
-};
-
-#ifdef CONFIG_KVM_DEBUG_FS
-#define HISTO_BUCKETS 30
-
-static struct kvm_spinlock_stats
-{
- u32 contention_stats[NR_CONTENTION_STATS];
- u32 histo_spin_blocked[HISTO_BUCKETS+1];
- u64 time_blocked;
-} spinlock_stats;
-
-static u8 zero_stats;
-
-static inline void check_zero(void)
-{
- u8 ret;
- u8 old;
-
- old = READ_ONCE(zero_stats);
- if (unlikely(old)) {
- ret = cmpxchg(&zero_stats, old, 0);
- /* This ensures only one fellow resets the stat */
- if (ret == old)
- memset(&spinlock_stats, 0, sizeof(spinlock_stats));
- }
-}
-
-static inline void add_stats(enum kvm_contention_stat var, u32 val)
-{
- check_zero();
- spinlock_stats.contention_stats[var] += val;
-}
-
-
-static inline u64 spin_time_start(void)
-{
- return sched_clock();
-}
-
-static void __spin_time_accum(u64 delta, u32 *array)
-{
- unsigned index;
-
- index = ilog2(delta);
- check_zero();
-
- if (index < HISTO_BUCKETS)
- array[index]++;
- else
- array[HISTO_BUCKETS]++;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
- u32 delta;
-
- delta = sched_clock() - start;
- __spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
- spinlock_stats.time_blocked += delta;
-}
-
-static struct dentry *d_spin_debug;
-static struct dentry *d_kvm_debug;
-
-static struct dentry *kvm_init_debugfs(void)
-{
- d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
- if (!d_kvm_debug)
- printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
-
- return d_kvm_debug;
-}
-
-static int __init kvm_spinlock_debugfs(void)
-{
- struct dentry *d_kvm;
-
- d_kvm = kvm_init_debugfs();
- if (d_kvm == NULL)
- return -ENOMEM;
-
- d_spin_debug = debugfs_create_dir("spinlocks", d_kvm);
-
- debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
-
- debugfs_create_u32("taken_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW]);
- debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
-
- debugfs_create_u32("released_slow", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW]);
- debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
- &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
-
- debugfs_create_u64("time_blocked", 0444, d_spin_debug,
- &spinlock_stats.time_blocked);
-
- debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
- spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
-
- return 0;
-}
-fs_initcall(kvm_spinlock_debugfs);
-#else /* !CONFIG_KVM_DEBUG_FS */
-static inline void add_stats(enum kvm_contention_stat var, u32 val)
-{
-}
-
-static inline u64 spin_time_start(void)
-{
- return 0;
-}
-
-static inline void spin_time_accum_blocked(u64 start)
-{
-}
-#endif /* CONFIG_KVM_DEBUG_FS */
-
-struct kvm_lock_waiting {
- struct arch_spinlock *lock;
- __ticket_t want;
-};
-
-/* cpus 'waiting' on a spinlock to become available */
-static cpumask_t waiting_cpus;
-
-/* Track spinlock on which a cpu is waiting */
-static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting);
-
-__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
-{
- struct kvm_lock_waiting *w;
- int cpu;
- u64 start;
- unsigned long flags;
- __ticket_t head;
-
- if (in_nmi())
- return;
-
- w = this_cpu_ptr(&klock_waiting);
- cpu = smp_processor_id();
- start = spin_time_start();
-
- /*
- * Make sure an interrupt handler can't upset things in a
- * partially setup state.
- */
- local_irq_save(flags);
-
- /*
- * The ordering protocol on this is that the "lock" pointer
- * may only be set non-NULL if the "want" ticket is correct.
- * If we're updating "want", we must first clear "lock".
- */
- w->lock = NULL;
- smp_wmb();
- w->want = want;
- smp_wmb();
- w->lock = lock;
-
- add_stats(TAKEN_SLOW, 1);
-
- /*
- * This uses set_bit, which is atomic but we should not rely on its
- * reordering gurantees. So barrier is needed after this call.
- */
- cpumask_set_cpu(cpu, &waiting_cpus);
-
- barrier();
-
- /*
- * Mark entry to slowpath before doing the pickup test to make
- * sure we don't deadlock with an unlocker.
- */
- __ticket_enter_slowpath(lock);
-
- /* make sure enter_slowpath, which is atomic does not cross the read */
- smp_mb__after_atomic();
-
- /*
- * check again make sure it didn't become free while
- * we weren't looking.
- */
- head = READ_ONCE(lock->tickets.head);
- if (__tickets_equal(head, want)) {
- add_stats(TAKEN_SLOW_PICKUP, 1);
- goto out;
- }
-
- /*
- * halt until it's our turn and kicked. Note that we do safe halt
- * for irq enabled case to avoid hang when lock info is overwritten
- * in irq spinlock slowpath and no spurious interrupt occur to save us.
- */
- if (arch_irqs_disabled_flags(flags))
- halt();
- else
- safe_halt();
-
-out:
- cpumask_clear_cpu(cpu, &waiting_cpus);
- w->lock = NULL;
- local_irq_restore(flags);
- spin_time_accum_blocked(start);
-}
-PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning);
-
-/* Kick vcpu waiting on @lock->head to reach value @ticket */
-static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
-{
- int cpu;
-
- add_stats(RELEASED_SLOW, 1);
- for_each_cpu(cpu, &waiting_cpus) {
- const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
- if (READ_ONCE(w->lock) == lock &&
- READ_ONCE(w->want) == ticket) {
- add_stats(RELEASED_SLOW_KICKED, 1);
- kvm_kick_cpu(cpu);
- break;
- }
- }
-}
-
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
-
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
-#ifdef CONFIG_QUEUED_SPINLOCKS
__pv_init_lock_hash();
pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = kvm_wait;
pv_lock_ops.kick = kvm_kick_cpu;
-#else /* !CONFIG_QUEUED_SPINLOCKS */
- pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
- pv_lock_ops.unlock_kick = kvm_unlock_kick;
-#endif
}
static __init int kvm_spinlock_init_jump(void)
return false;
}
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
#endif
#endif
{ NULL, },
};
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
/*
- * set_sched_topology() sets the topology internal to a CPU. The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called. It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
*/
-static void primarily_use_numa_for_topology(void)
-{
- set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package;
void set_cpu_sibling_map(int cpu)
{
c->booted_cores = cpu_data(i).booted_cores;
}
if (match_die(c, o) && !topology_same_node(c, o))
- primarily_use_numa_for_topology();
+ x86_has_numa_in_package = true;
}
threads = cpumask_weight(topology_sibling_cpumask(cpu));
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
maxlvt = lapic_get_maxlvt();
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
/*
* Be paranoid about clearing APIC errors.
*/
- if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
* Determine this based on the APIC version.
* If we don't have an integrated APIC, don't send the STARTUP IPIs.
*/
- if (APIC_INTEGRATED(apic_version[phys_apicid]))
+ if (APIC_INTEGRATED(boot_cpu_apic_version))
num_starts = 2;
else
num_starts = 0;
per_cpu(cpu_current_top_of_stack, cpu) =
(unsigned long)task_stack_page(idle) + THREAD_SIZE;
#else
- clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
#endif
}
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
- stack_start = idle->thread.sp;
+ initial_stack = idle->thread.sp;
/*
* Enable the espfix hack for this CPU
/*
* Be paranoid about clearing APIC errors.
*/
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ if (APIC_INTEGRATED(boot_cpu_apic_version)) {
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
common_cpu_up(cpu, tidle);
- /*
- * We have to walk the irq descriptors to setup the vector
- * space for the cpu which comes online. Prevent irq
- * alloc/free across the bringup.
- */
- irq_lock_sparse();
-
err = do_boot_cpu(apicid, cpu, tidle);
-
if (err) {
- irq_unlock_sparse();
pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
return -EIO;
}
touch_nmi_watchdog();
}
- irq_unlock_sparse();
-
return 0;
}
/*
* If we couldn't find a local APIC, then get out of here now!
*/
- if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
+ if (APIC_INTEGRATED(boot_cpu_apic_version) &&
!boot_cpu_has(X86_FEATURE_APIC)) {
if (!disable_apic) {
pr_err("BIOS bug, local APIC #%d not detected!...\n",
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
+
+ /*
+ * Set 'default' x86 topology, this matches default_topology() in that
+ * it has NUMA nodes as a topology level. See also
+ * native_smp_cpus_done().
+ *
+ * Must be done before set_cpus_sibling_map() is ran.
+ */
+ set_sched_topology(x86_topology);
+
set_cpu_sibling_map(0);
switch (smp_sanity_check(max_cpus)) {
break;
}
- default_setup_apic_routing();
-
if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
+ default_setup_apic_routing();
cpu0_logical_apicid = apic_bsp_setup(false);
pr_info("CPU%d: ", 0);
{
pr_debug("Boot done\n");
+ if (x86_has_numa_in_package)
+ set_sched_topology(x86_numa_in_package_topology);
+
nmi_selftest();
impress_friends();
setup_ioapic_dest();
static int __acpi_processor_start(struct acpi_device *device);
- static int acpi_cpu_soft_notify(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+ static int acpi_soft_cpu_online(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
struct acpi_processor *pr = per_cpu(processors, cpu);
struct acpi_device *device;
- action &= ~CPU_TASKS_FROZEN;
-
- switch (action) {
- case CPU_ONLINE:
- case CPU_DEAD:
- break;
- default:
- return NOTIFY_DONE;
- }
if (!pr || acpi_bus_get_device(pr->handle, &device))
- return NOTIFY_DONE;
-
- if (action == CPU_ONLINE) {
- /*
- * CPU got physically hotplugged and onlined for the first time:
- * Initialize missing things.
- */
- if (pr->flags.need_hotplug_init) {
- int ret;
-
- pr_info("Will online and init hotplugged CPU: %d\n",
- pr->id);
- pr->flags.need_hotplug_init = 0;
- ret = __acpi_processor_start(device);
- WARN(ret, "Failed to start CPU: %d\n", pr->id);
- } else {
- /* Normal CPU soft online event. */
- acpi_processor_ppc_has_changed(pr, 0);
- acpi_processor_hotplug(pr);
- acpi_processor_reevaluate_tstate(pr, action);
- acpi_processor_tstate_has_changed(pr);
- }
- } else if (action == CPU_DEAD) {
- /* Invalidate flag.throttling after the CPU is offline. */
- acpi_processor_reevaluate_tstate(pr, action);
+ return 0;
+ /*
+ * CPU got physically hotplugged and onlined for the first time:
+ * Initialize missing things.
+ */
+ if (pr->flags.need_hotplug_init) {
+ int ret;
+
+ pr_info("Will online and init hotplugged CPU: %d\n",
+ pr->id);
+ pr->flags.need_hotplug_init = 0;
+ ret = __acpi_processor_start(device);
+ WARN(ret, "Failed to start CPU: %d\n", pr->id);
+ } else {
+ /* Normal CPU soft online event. */
+ acpi_processor_ppc_has_changed(pr, 0);
+ acpi_processor_hotplug(pr);
+ acpi_processor_reevaluate_tstate(pr, false);
+ acpi_processor_tstate_has_changed(pr);
}
- return NOTIFY_OK;
+ return 0;
}
- static struct notifier_block acpi_cpu_notifier = {
- .notifier_call = acpi_cpu_soft_notify,
- };
+ static int acpi_soft_cpu_dead(unsigned int cpu)
+ {
+ struct acpi_processor *pr = per_cpu(processors, cpu);
+ struct acpi_device *device;
+
+ if (!pr || acpi_bus_get_device(pr->handle, &device))
+ return 0;
+
+ acpi_processor_reevaluate_tstate(pr, true);
+ return 0;
+ }
#ifdef CONFIG_ACPI_CPU_FREQ_PSS
static int acpi_pss_perf_init(struct acpi_processor *pr,
return 0;
result = acpi_cppc_processor_probe(pr);
- if (result)
- return -ENODEV;
+ if (result && !IS_ENABLED(CONFIG_ACPI_CPU_FREQ_PSS))
+ dev_warn(&device->dev, "CPPC data invalid or not present\n");
if (!cpuidle_get_driver() || cpuidle_get_driver() == &acpi_idle_driver)
acpi_processor_power_init(pr);
* This is needed for the powernow-k8 driver, that works even without
* ACPI, but needs symbols from this driver
*/
-
+ static enum cpuhp_state hp_online;
static int __init acpi_processor_driver_init(void)
{
int result = 0;
if (result < 0)
return result;
- register_hotcpu_notifier(&acpi_cpu_notifier);
+ result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+ "acpi/cpu-drv:online",
+ acpi_soft_cpu_online, NULL);
+ if (result < 0)
+ goto err;
+ hp_online = result;
+ cpuhp_setup_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD, "acpi/cpu-drv:dead",
+ NULL, acpi_soft_cpu_dead);
+
acpi_thermal_cpufreq_init();
acpi_processor_ppc_init();
acpi_processor_throttling_init();
return 0;
+ err:
+ driver_unregister(&acpi_processor_driver);
+ return result;
}
static void __exit acpi_processor_driver_exit(void)
acpi_processor_ppc_exit();
acpi_thermal_cpufreq_exit();
- unregister_hotcpu_notifier(&acpi_cpu_notifier);
+ cpuhp_remove_state_nocalls(hp_online);
+ cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD);
driver_unregister(&acpi_processor_driver);
}
int num_cntrs;
atomic_t active_events;
struct mutex reserve_mutex;
- struct list_head entry;
+ struct hlist_node node;
cpumask_t cpus;
};
#define to_cci_pmu(c) (container_of(c, struct cci_pmu, pmu))
- static DEFINE_MUTEX(cci_pmu_mutex);
- static LIST_HEAD(cci_pmu_list);
-
enum cci_models {
#ifdef CONFIG_ARM_CCI400_PMU
CCI400_R0,
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_wrq, 0xB),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_cd_hs, 0xC),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_rq_stall_addr_hazard, 0xD),
- CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snopp_rq_stall_tt_full, 0xE),
+ CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_rq_stall_tt_full, 0xE),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_rq_tzmp1_prot, 0xF),
NULL
};
return perf_pmu_register(&cci_pmu->pmu, name, -1);
}
- static int cci_pmu_offline_cpu(unsigned int cpu)
+ static int cci_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
{
- struct cci_pmu *cci_pmu;
+ struct cci_pmu *cci_pmu = hlist_entry_safe(node, struct cci_pmu, node);
unsigned int target;
- mutex_lock(&cci_pmu_mutex);
- list_for_each_entry(cci_pmu, &cci_pmu_list, entry) {
- if (!cpumask_test_and_clear_cpu(cpu, &cci_pmu->cpus))
- continue;
- target = cpumask_any_but(cpu_online_mask, cpu);
- if (target >= nr_cpu_ids)
- continue;
- /*
- * TODO: migrate context once core races on event->ctx have
- * been fixed.
- */
- cpumask_set_cpu(target, &cci_pmu->cpus);
- }
- mutex_unlock(&cci_pmu_mutex);
+ if (!cpumask_test_and_clear_cpu(cpu, &cci_pmu->cpus))
+ return 0;
+ target = cpumask_any_but(cpu_online_mask, cpu);
+ if (target >= nr_cpu_ids)
+ return 0;
+ /*
+ * TODO: migrate context once core races on event->ctx have
+ * been fixed.
+ */
+ cpumask_set_cpu(target, &cci_pmu->cpus);
return 0;
}
if (ret)
return ret;
- mutex_lock(&cci_pmu_mutex);
- list_add(&cci_pmu->entry, &cci_pmu_list);
- mutex_unlock(&cci_pmu_mutex);
-
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
+ &cci_pmu->node);
pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
return 0;
}
{
int ret;
- ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
- "AP_PERF_ARM_CCI_ONLINE", NULL,
- cci_pmu_offline_cpu);
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
+ "AP_PERF_ARM_CCI_ONLINE", NULL,
+ cci_pmu_offline_cpu);
if (ret)
return ret;
struct hrtimer hrtimer;
cpumask_t cpu;
- struct list_head entry;
+ struct hlist_node node;
struct pmu pmu;
};
struct arm_ccn_component *xp;
struct arm_ccn_dt dt;
+ int mn_id;
};
- static DEFINE_MUTEX(arm_ccn_mutex);
- static LIST_HEAD(arm_ccn_list);
-
static int arm_ccn_node_to_xp(int node)
{
return node / CCN_NUM_XP_PORTS;
#define CCN_CONFIG_TYPE(_config) (((_config) >> 8) & 0xff)
#define CCN_CONFIG_EVENT(_config) (((_config) >> 16) & 0xff)
#define CCN_CONFIG_PORT(_config) (((_config) >> 24) & 0x3)
+#define CCN_CONFIG_BUS(_config) (((_config) >> 24) & 0x3)
#define CCN_CONFIG_VC(_config) (((_config) >> 26) & 0x7)
#define CCN_CONFIG_DIR(_config) (((_config) >> 29) & 0x1)
#define CCN_CONFIG_MASK(_config) (((_config) >> 30) & 0xf)
static CCN_FORMAT_ATTR(type, "config:8-15");
static CCN_FORMAT_ATTR(event, "config:16-23");
static CCN_FORMAT_ATTR(port, "config:24-25");
+static CCN_FORMAT_ATTR(bus, "config:24-25");
static CCN_FORMAT_ATTR(vc, "config:26-28");
static CCN_FORMAT_ATTR(dir, "config:29-29");
static CCN_FORMAT_ATTR(mask, "config:30-33");
&arm_ccn_pmu_format_attr_type.attr.attr,
&arm_ccn_pmu_format_attr_event.attr.attr,
&arm_ccn_pmu_format_attr_port.attr.attr,
+ &arm_ccn_pmu_format_attr_bus.attr.attr,
&arm_ccn_pmu_format_attr_vc.attr.attr,
&arm_ccn_pmu_format_attr_dir.attr.attr,
&arm_ccn_pmu_format_attr_mask.attr.attr,
static ssize_t arm_ccn_pmu_event_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
struct arm_ccn_pmu_event *event = container_of(attr,
struct arm_ccn_pmu_event, attr);
ssize_t res;
break;
case CCN_TYPE_XP:
res += snprintf(buf + res, PAGE_SIZE - res,
- ",xp=?,port=?,vc=?,dir=?");
+ ",xp=?,vc=?");
if (event->event == CCN_EVENT_WATCHPOINT)
res += snprintf(buf + res, PAGE_SIZE - res,
- ",cmp_l=?,cmp_h=?,mask=?");
+ ",port=?,dir=?,cmp_l=?,cmp_h=?,mask=?");
+ else
+ res += snprintf(buf + res, PAGE_SIZE - res,
+ ",bus=?");
+
+ break;
+ case CCN_TYPE_MN:
+ res += snprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id);
break;
default:
res += snprintf(buf + res, PAGE_SIZE - res, ",node=?");
}
static struct arm_ccn_pmu_event arm_ccn_pmu_events[] = {
- CCN_EVENT_MN(eobarrier, "dir=0,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
- CCN_EVENT_MN(ecbarrier, "dir=0,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
- CCN_EVENT_MN(dvmop, "dir=0,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(eobarrier, "dir=1,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(ecbarrier, "dir=1,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(dvmop, "dir=1,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
CCN_EVENT_HNI(txdatflits, "dir=1,vc=3", CCN_IDX_MASK_ANY),
CCN_EVENT_HNI(rxdatflits, "dir=0,vc=3", CCN_IDX_MASK_ANY),
CCN_EVENT_HNI(txreqflits, "dir=1,vc=0", CCN_IDX_MASK_ANY),
if (has_branch_stack(event) || event->attr.exclude_user ||
event->attr.exclude_kernel || event->attr.exclude_hv ||
- event->attr.exclude_idle) {
+ event->attr.exclude_idle || event->attr.exclude_host ||
+ event->attr.exclude_guest) {
dev_warn(ccn->dev, "Can't exclude execution levels!\n");
- return -EOPNOTSUPP;
+ return -EINVAL;
}
if (event->cpu < 0) {
/* Validate node/xp vs topology */
switch (type) {
+ case CCN_TYPE_MN:
+ if (node_xp != ccn->mn_id) {
+ dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp);
+ return -EINVAL;
+ }
+ break;
case CCN_TYPE_XP:
if (node_xp >= ccn->num_xps) {
dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp);
struct arm_ccn_component *xp;
u32 val, dt_cfg;
+ /* Nothing to do for cycle counter */
+ if (hw->idx == CCN_IDX_PMU_CYCLE_COUNTER)
+ return;
+
if (CCN_CONFIG_TYPE(event->attr.config) == CCN_TYPE_XP)
xp = &ccn->xp[CCN_CONFIG_XP(event->attr.config)];
else
arm_ccn_pmu_read_counter(ccn, hw->idx));
hw->state = 0;
- /*
- * Pin the timer, so that the overflows are handled by the chosen
- * event->cpu (this is the same one as presented in "cpumask"
- * attribute).
- */
- if (!ccn->irq)
- hrtimer_start(&ccn->dt.hrtimer, arm_ccn_pmu_timer_period(),
- HRTIMER_MODE_REL_PINNED);
-
/* Set the DT bus input, engaging the counter */
arm_ccn_pmu_xp_dt_config(event, 1);
}
static void arm_ccn_pmu_event_stop(struct perf_event *event, int flags)
{
- struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
struct hw_perf_event *hw = &event->hw;
- u64 timeout;
/* Disable counting, setting the DT bus to pass-through mode */
arm_ccn_pmu_xp_dt_config(event, 0);
- if (!ccn->irq)
- hrtimer_cancel(&ccn->dt.hrtimer);
-
- /* Let the DT bus drain */
- timeout = arm_ccn_pmu_read_counter(ccn, CCN_IDX_PMU_CYCLE_COUNTER) +
- ccn->num_xps;
- while (arm_ccn_pmu_read_counter(ccn, CCN_IDX_PMU_CYCLE_COUNTER) <
- timeout)
- cpu_relax();
-
if (flags & PERF_EF_UPDATE)
arm_ccn_pmu_event_update(event);
/* Comparison values */
writel(cmp_l & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_L(wp));
- writel((cmp_l >> 32) & 0xefffffff,
+ writel((cmp_l >> 32) & 0x7fffffff,
source->base + CCN_XP_DT_CMP_VAL_L(wp) + 4);
writel(cmp_h & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_H(wp));
writel((cmp_h >> 32) & 0x0fffffff,
/* Mask */
writel(mask_l & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_L(wp));
- writel((mask_l >> 32) & 0xefffffff,
+ writel((mask_l >> 32) & 0x7fffffff,
source->base + CCN_XP_DT_CMP_MASK_L(wp) + 4);
writel(mask_h & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_H(wp));
writel((mask_h >> 32) & 0x0fffffff,
hw->event_base = CCN_XP_DT_CONFIG__DT_CFG__XP_PMU_EVENT(hw->config_base);
id = (CCN_CONFIG_VC(event->attr.config) << 4) |
- (CCN_CONFIG_PORT(event->attr.config) << 3) |
+ (CCN_CONFIG_BUS(event->attr.config) << 3) |
(CCN_CONFIG_EVENT(event->attr.config) << 0);
val = readl(source->base + CCN_XP_PMU_EVENT_SEL);
spin_unlock(&ccn->dt.config_lock);
}
+static int arm_ccn_pmu_active_counters(struct arm_ccn *ccn)
+{
+ return bitmap_weight(ccn->dt.pmu_counters_mask,
+ CCN_NUM_PMU_EVENT_COUNTERS + 1);
+}
+
static int arm_ccn_pmu_event_add(struct perf_event *event, int flags)
{
int err;
struct hw_perf_event *hw = &event->hw;
+ struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
err = arm_ccn_pmu_event_alloc(event);
if (err)
return err;
+ /*
+ * Pin the timer, so that the overflows are handled by the chosen
+ * event->cpu (this is the same one as presented in "cpumask"
+ * attribute).
+ */
+ if (!ccn->irq && arm_ccn_pmu_active_counters(ccn) == 1)
+ hrtimer_start(&ccn->dt.hrtimer, arm_ccn_pmu_timer_period(),
+ HRTIMER_MODE_REL_PINNED);
+
arm_ccn_pmu_event_config(event);
hw->state = PERF_HES_STOPPED;
static void arm_ccn_pmu_event_del(struct perf_event *event, int flags)
{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
+
arm_ccn_pmu_event_stop(event, PERF_EF_UPDATE);
arm_ccn_pmu_event_release(event);
+
+ if (!ccn->irq && arm_ccn_pmu_active_counters(ccn) == 0)
+ hrtimer_cancel(&ccn->dt.hrtimer);
}
static void arm_ccn_pmu_event_read(struct perf_event *event)
arm_ccn_pmu_event_update(event);
}
+static void arm_ccn_pmu_enable(struct pmu *pmu)
+{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(pmu);
+
+ u32 val = readl(ccn->dt.base + CCN_DT_PMCR);
+ val |= CCN_DT_PMCR__PMU_EN;
+ writel(val, ccn->dt.base + CCN_DT_PMCR);
+}
+
+static void arm_ccn_pmu_disable(struct pmu *pmu)
+{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(pmu);
+
+ u32 val = readl(ccn->dt.base + CCN_DT_PMCR);
+ val &= ~CCN_DT_PMCR__PMU_EN;
+ writel(val, ccn->dt.base + CCN_DT_PMCR);
+}
+
static irqreturn_t arm_ccn_pmu_overflow_handler(struct arm_ccn_dt *dt)
{
u32 pmovsr = readl(dt->base + CCN_DT_PMOVSR);
}
- static int arm_ccn_pmu_offline_cpu(unsigned int cpu)
+ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
{
- struct arm_ccn_dt *dt;
+ struct arm_ccn_dt *dt = hlist_entry_safe(node, struct arm_ccn_dt, node);
+ struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
unsigned int target;
- mutex_lock(&arm_ccn_mutex);
- list_for_each_entry(dt, &arm_ccn_list, entry) {
- struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
-
- if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
- continue;
- target = cpumask_any_but(cpu_online_mask, cpu);
- if (target >= nr_cpu_ids)
- continue;
- perf_pmu_migrate_context(&dt->pmu, cpu, target);
- cpumask_set_cpu(target, &dt->cpu);
- if (ccn->irq)
- WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
- }
- mutex_unlock(&arm_ccn_mutex);
+ if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+ return 0;
+ target = cpumask_any_but(cpu_online_mask, cpu);
+ if (target >= nr_cpu_ids)
+ return 0;
+ perf_pmu_migrate_context(&dt->pmu, cpu, target);
+ cpumask_set_cpu(target, &dt->cpu);
+ if (ccn->irq)
+ WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
return 0;
}
-
static DEFINE_IDA(arm_ccn_pmu_ida);
static int arm_ccn_pmu_init(struct arm_ccn *ccn)
.start = arm_ccn_pmu_event_start,
.stop = arm_ccn_pmu_event_stop,
.read = arm_ccn_pmu_event_read,
+ .pmu_enable = arm_ccn_pmu_enable,
+ .pmu_disable = arm_ccn_pmu_disable,
};
/* No overflow interrupt? Have to use a timer instead. */
if (err)
goto error_pmu_register;
- mutex_lock(&arm_ccn_mutex);
- list_add(&ccn->dt.entry, &arm_ccn_list);
- mutex_unlock(&arm_ccn_mutex);
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
return 0;
error_pmu_register:
{
int i;
- mutex_lock(&arm_ccn_mutex);
- list_del(&ccn->dt.entry);
- mutex_unlock(&arm_ccn_mutex);
-
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
if (ccn->irq)
irq_set_affinity_hint(ccn->irq, NULL);
for (i = 0; i < ccn->num_xps; i++)
switch (type) {
case CCN_TYPE_MN:
+ ccn->mn_id = id;
+ return 0;
case CCN_TYPE_DT:
return 0;
case CCN_TYPE_XP:
/* Can set 'disable' bits, so can acknowledge interrupts */
writel(CCN_MN_ERRINT_STATUS__PMU_EVENTS__ENABLE,
ccn->base + CCN_MN_ERRINT_STATUS);
- err = devm_request_irq(ccn->dev, irq, arm_ccn_irq_handler, 0,
- dev_name(ccn->dev), ccn);
+ err = devm_request_irq(ccn->dev, irq, arm_ccn_irq_handler,
+ IRQF_NOBALANCING | IRQF_NO_THREAD,
+ dev_name(ccn->dev), ccn);
if (err)
return err;
{
int i, ret;
- ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
- "AP_PERF_ARM_CCN_ONLINE", NULL,
- arm_ccn_pmu_offline_cpu);
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ "AP_PERF_ARM_CCN_ONLINE", NULL,
+ arm_ccn_pmu_offline_cpu);
if (ret)
return ret;
static void __exit arm_ccn_exit(void)
{
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE);
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
platform_driver_unregister(&arm_ccn_driver);
}
.release = cpufreq_sysfs_release,
};
-static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+static int add_cpu_dev_symlink(struct cpufreq_policy *policy,
+ struct device *dev)
{
- struct device *cpu_dev;
-
- pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);
-
- if (!policy)
- return 0;
-
- cpu_dev = get_cpu_device(cpu);
- if (WARN_ON(!cpu_dev))
- return 0;
-
- return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
-}
-
-static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
-{
- struct device *cpu_dev;
-
- pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);
-
- cpu_dev = get_cpu_device(cpu);
- if (WARN_ON(!cpu_dev))
- return;
-
- sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
+ dev_dbg(dev, "%s: Adding symlink\n", __func__);
+ return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
}
-/* Add/remove symlinks for all related CPUs */
-static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
+static void remove_cpu_dev_symlink(struct cpufreq_policy *policy,
+ struct device *dev)
{
- unsigned int j;
- int ret = 0;
-
- /* Some related CPUs might not be present (physically hotplugged) */
- for_each_cpu(j, policy->real_cpus) {
- ret = add_cpu_dev_symlink(policy, j);
- if (ret)
- break;
- }
-
- return ret;
-}
-
-static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
-{
- unsigned int j;
-
- /* Some related CPUs might not be present (physically hotplugged) */
- for_each_cpu(j, policy->real_cpus)
- remove_cpu_dev_symlink(policy, j);
+ dev_dbg(dev, "%s: Removing symlink\n", __func__);
+ sysfs_remove_link(&dev->kobj, "cpufreq");
}
static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
return ret;
}
- return cpufreq_add_dev_symlink(policy);
+ return 0;
}
__weak struct cpufreq_governor *cpufreq_default_governor(void)
static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
{
- struct device *dev = get_cpu_device(cpu);
struct cpufreq_policy *policy;
int ret;
- if (WARN_ON(!dev))
- return NULL;
-
policy = kzalloc(sizeof(*policy), GFP_KERNEL);
if (!policy)
return NULL;
down_write(&policy->rwsem);
cpufreq_stats_free_table(policy);
- cpufreq_remove_dev_symlink(policy);
kobj = &policy->kobj;
cmp = &policy->kobj_unregister;
up_write(&policy->rwsem);
if (new_policy) {
/* related_cpus should at least include policy->cpus. */
cpumask_copy(policy->related_cpus, policy->cpus);
- /* Remember CPUs present at the policy creation time. */
- cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+ /* Clear mask of registered CPUs */
+ cpumask_clear(policy->real_cpus);
}
/*
return ret;
}
- static void cpufreq_offline(unsigned int cpu);
++static int cpufreq_offline(unsigned int cpu);
+
/**
* cpufreq_add_dev - the cpufreq interface for a CPU device.
* @dev: CPU device.
{
struct cpufreq_policy *policy;
unsigned cpu = dev->id;
+ int ret;
dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);
- if (cpu_online(cpu))
- return cpufreq_online(cpu);
+ if (cpu_online(cpu)) {
+ ret = cpufreq_online(cpu);
+ if (ret)
+ return ret;
+ }
- /*
- * A hotplug notifier will follow and we will handle it as CPU online
- * then. For now, just create the sysfs link, unless there is no policy
- * or the link is already present.
- */
+ /* Create sysfs link on CPU registration */
policy = per_cpu(cpufreq_cpu_data, cpu);
if (!policy || cpumask_test_and_set_cpu(cpu, policy->real_cpus))
return 0;
- return add_cpu_dev_symlink(policy, cpu);
+ ret = add_cpu_dev_symlink(policy, dev);
+ if (ret) {
+ cpumask_clear_cpu(cpu, policy->real_cpus);
+ cpufreq_offline(cpu);
+ }
+
+ return ret;
}
- static void cpufreq_offline(unsigned int cpu)
+ static int cpufreq_offline(unsigned int cpu)
{
struct cpufreq_policy *policy;
int ret;
policy = cpufreq_cpu_get_raw(cpu);
if (!policy) {
pr_debug("%s: No cpu_data found\n", __func__);
- return;
+ return 0;
}
down_write(&policy->rwsem);
unlock:
up_write(&policy->rwsem);
+ return 0;
}
/**
cpufreq_offline(cpu);
cpumask_clear_cpu(cpu, policy->real_cpus);
- remove_cpu_dev_symlink(policy, cpu);
+ remove_cpu_dev_symlink(policy, dev);
if (cpumask_empty(policy->real_cpus))
cpufreq_policy_free(policy, true);
}
EXPORT_SYMBOL(cpufreq_update_policy);
- static int cpufreq_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
- {
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- cpufreq_online(cpu);
- break;
-
- case CPU_DOWN_PREPARE:
- cpufreq_offline(cpu);
- break;
- }
- return NOTIFY_OK;
- }
-
- static struct notifier_block __refdata cpufreq_cpu_notifier = {
- .notifier_call = cpufreq_cpu_callback,
- };
-
/*********************************************************************
* BOOST *
*********************************************************************/
/*********************************************************************
* REGISTER / UNREGISTER CPUFREQ DRIVER *
*********************************************************************/
+ static enum cpuhp_state hp_online;
/**
* cpufreq_register_driver - register a CPU Frequency driver
goto err_if_unreg;
}
- register_hotcpu_notifier(&cpufreq_cpu_notifier);
+ ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
+ cpufreq_online,
+ cpufreq_offline);
+ if (ret < 0)
+ goto err_if_unreg;
+ hp_online = ret;
+ ret = 0;
+
pr_debug("driver %s up and running\n", driver_data->name);
goto out;
get_online_cpus();
subsys_interface_unregister(&cpufreq_interface);
remove_boost_sysfs_file();
- unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
+ cpuhp_remove_state_nocalls(hp_online);
write_lock_irqsave(&cpufreq_driver_lock, flags);
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
+ int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
+ int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(bi);
bi->bi_bdev = rdev->bdev;
bio_set_op_attrs(bi, op, op_flags);
bi->bi_end_io = op_is_write(op)
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
bio_set_op_attrs(rbi, op, op_flags);
BUG_ON(!op_is_write(op));
put_cpu();
}
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+ int disks)
{
struct stripe_head *sh;
+ int i;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
atomic_set(&sh->count, 1);
+ for (i = 0; i < disks; i++) {
+ struct r5dev *dev = &sh->dev[i];
+
+ bio_init(&dev->req);
+ dev->req.bi_io_vec = &dev->vec;
+ dev->req.bi_max_vecs = 1;
+
+ bio_init(&dev->rreq);
+ dev->rreq.bi_io_vec = &dev->rvec;
+ dev->rreq.bi_max_vecs = 1;
+ }
}
return sh;
}
{
struct stripe_head *sh;
- sh = alloc_stripe(conf->slab_cache, gfp);
+ sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
if (!sh)
return 0;
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
- nsh = alloc_stripe(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
if (!nsh)
break;
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
}
}
rdev_dec_pending(rdev, conf->mddev);
+ bio_reset(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
+ bio_reset(bi);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
{
struct r5dev *dev = &sh->dev[i];
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_max_vecs = 1;
- dev->req.bi_private = sh;
-
- bio_init(&dev->rreq);
- dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_max_vecs = 1;
- dev->rreq.bi_private = sh;
-
dev->flags = 0;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
}
if (!bio_list_empty(&s.return_bi)) {
- if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+ (s.failed <= conf->max_degraded ||
+ conf->mddev->external == 0)) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->return_bi, &s.return_bi);
spin_unlock_irq(&conf->device_lock);
return 0;
}
- static void raid5_free_percpu(struct r5conf *conf)
+ static int raid456_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
- unsigned long cpu;
+ struct r5conf *conf = hlist_entry_safe(node, struct r5conf, node);
+
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+ return 0;
+ }
+ static void raid5_free_percpu(struct r5conf *conf)
+ {
if (!conf->percpu)
return;
- #ifdef CONFIG_HOTPLUG_CPU
- unregister_cpu_notifier(&conf->cpu_notify);
- #endif
-
- get_online_cpus();
- for_each_possible_cpu(cpu)
- free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
- put_online_cpus();
-
+ cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
free_percpu(conf->percpu);
}
kfree(conf);
}
- #ifdef CONFIG_HOTPLUG_CPU
- static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
- void *hcpu)
+ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
{
- struct r5conf *conf = container_of(nfb, struct r5conf, cpu_notify);
- long cpu = (long)hcpu;
+ struct r5conf *conf = hlist_entry_safe(node, struct r5conf, node);
struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu);
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- if (alloc_scratch_buffer(conf, percpu)) {
- pr_err("%s: failed memory allocation for cpu%ld\n",
- __func__, cpu);
- return notifier_from_errno(-ENOMEM);
- }
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
- break;
- default:
- break;
+ if (alloc_scratch_buffer(conf, percpu)) {
+ pr_err("%s: failed memory allocation for cpu%u\n",
+ __func__, cpu);
+ return -ENOMEM;
}
- return NOTIFY_OK;
+ return 0;
}
- #endif
static int raid5_alloc_percpu(struct r5conf *conf)
{
- unsigned long cpu;
int err = 0;
conf->percpu = alloc_percpu(struct raid5_percpu);
if (!conf->percpu)
return -ENOMEM;
- #ifdef CONFIG_HOTPLUG_CPU
- conf->cpu_notify.notifier_call = raid456_cpu_notify;
- conf->cpu_notify.priority = 0;
- err = register_cpu_notifier(&conf->cpu_notify);
- if (err)
- return err;
- #endif
-
- get_online_cpus();
- for_each_present_cpu(cpu) {
- err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
- if (err) {
- pr_err("%s: failed memory allocation for cpu%ld\n",
- __func__, cpu);
- break;
- }
- }
- put_online_cpus();
-
+ err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
if (!err) {
conf->scribble_disks = max(conf->raid_disks,
conf->previous_raid_disks);
}
conf->min_nr_stripes = NR_STRIPES;
+ if (mddev->reshape_position != MaxSector) {
+ int stripes = max_t(int,
+ ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ conf->min_nr_stripes = max(NR_STRIPES, stripes);
+ if (conf->min_nr_stripes != NR_STRIPES)
+ printk(KERN_INFO
+ "md/raid:%s: force stripe size %d for reshape\n",
+ mdname(mddev), conf->min_nr_stripes);
+ }
memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
- printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
- mdname(mddev));
- mddev->ro = 1;
- set_disk_ro(mddev->gendisk, 1);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+ if (!journal_dev) {
+ pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ } else if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
}
conf->min_offset_diff = min_offset_diff;
static int __init raid5_init(void)
{
+ int ret;
+
raid5_wq = alloc_workqueue("raid5wq",
WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0);
if (!raid5_wq)
return -ENOMEM;
+
+ ret = cpuhp_setup_state_multi(CPUHP_MD_RAID5_PREPARE,
+ "md/raid5:prepare",
+ raid456_cpu_up_prepare,
+ raid456_cpu_dead);
+ if (ret) {
+ destroy_workqueue(raid5_wq);
+ return ret;
+ }
register_md_personality(&raid6_personality);
register_md_personality(&raid5_personality);
register_md_personality(&raid4_personality);
unregister_md_personality(&raid6_personality);
unregister_md_personality(&raid5_personality);
unregister_md_personality(&raid4_personality);
+ cpuhp_remove_multi_state(CPUHP_MD_RAID5_PREPARE);
destroy_workqueue(raid5_wq);
}
return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
}
+static ssize_t armpmu_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
+ return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
+}
+
+static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+
+static struct attribute *armpmu_common_attrs[] = {
+ &dev_attr_cpus.attr,
+ NULL,
+};
+
+static struct attribute_group armpmu_common_attr_group = {
+ .attrs = armpmu_common_attrs,
+};
+
static void armpmu_init(struct arm_pmu *armpmu)
{
atomic_set(&armpmu->active_events, 0);
.stop = armpmu_stop,
.read = armpmu_read,
.filter_match = armpmu_filter_match,
+ .attr_groups = armpmu->attr_groups,
};
+ armpmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =
+ &armpmu_common_attr_group;
}
/* Set at runtime when we know what CPU type we are. */
irqs = min(pmu_device->num_resources, num_possible_cpus());
irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
on_each_cpu_mask(&cpu_pmu->supported_cpus,
cpu_pmu_disable_percpu_irq, &irq, 1);
free_percpu_irq(irq, &hw_events->percpu_pmu);
if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
- if (irq >= 0)
+ if (irq > 0)
free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
}
}
}
irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
err = request_percpu_irq(irq, handler, "arm-pmu",
&hw_events->percpu_pmu);
if (err) {
return 0;
}
- static DEFINE_SPINLOCK(arm_pmu_lock);
- static LIST_HEAD(arm_pmu_list);
-
/*
* PMU hardware loses all context when a CPU goes offline.
* When a CPU is hotplugged back in, since some hardware registers are
* UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
* junk values out of them.
*/
- static int arm_perf_starting_cpu(unsigned int cpu)
+ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
{
- struct arm_pmu *pmu;
-
- spin_lock(&arm_pmu_lock);
- list_for_each_entry(pmu, &arm_pmu_list, entry) {
+ struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node);
- if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
- continue;
- if (pmu->reset)
- pmu->reset(pmu);
- }
- spin_unlock(&arm_pmu_lock);
+ if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
+ return 0;
+ if (pmu->reset)
+ pmu->reset(pmu);
return 0;
}
if (!cpu_hw_events)
return -ENOMEM;
- spin_lock(&arm_pmu_lock);
- list_add_tail(&cpu_pmu->entry, &arm_pmu_list);
- spin_unlock(&arm_pmu_lock);
+ err = cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+ &cpu_pmu->node);
+ if (err)
+ goto out_free;
err = cpu_pm_pmu_register(cpu_pmu);
if (err)
return 0;
out_unregister:
- spin_lock(&arm_pmu_lock);
- list_del(&cpu_pmu->entry);
- spin_unlock(&arm_pmu_lock);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+ &cpu_pmu->node);
+ out_free:
free_percpu(cpu_hw_events);
return err;
}
static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
{
cpu_pm_pmu_unregister(cpu_pmu);
- spin_lock(&arm_pmu_lock);
- list_del(&cpu_pmu->entry);
- spin_unlock(&arm_pmu_lock);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+ &cpu_pmu->node);
free_percpu(cpu_pmu->hw_events);
}
/* Check the IRQ type and prohibit a mix of PPIs and SPIs */
irq = platform_get_irq(pdev, i);
- if (irq >= 0) {
+ if (irq > 0) {
bool spi = !irq_is_percpu(irq);
if (i > 0 && spi != using_spi) {
pr_err("PPI/SPI IRQ type mismatch for %s!\n",
dn->name);
+ of_node_put(dn);
kfree(irqs);
return -EINVAL;
}
if (cpumask_weight(&pmu->supported_cpus) == 0) {
int irq = platform_get_irq(pdev, 0);
- if (irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
/* If using PPIs, check the affinity of the partition */
int ret;
ret = of_pmu_irq_cfg(pmu);
if (!ret)
ret = init_fn(pmu);
- } else {
+ } else if (probe_table) {
cpumask_setall(&pmu->supported_cpus);
ret = probe_current_pmu(pmu, probe_table);
}
goto out_free;
}
+
ret = cpu_pmu_init(pmu);
if (ret)
goto out_free;
{
int ret;
- ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_STARTING,
- "AP_PERF_ARM_STARTING",
- arm_perf_starting_cpu, NULL);
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
+ "AP_PERF_ARM_STARTING",
+ arm_perf_starting_cpu, NULL);
if (ret)
pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
ret);
#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */
#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */
#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */
- #define CPU_DYING 0x0008 /* CPU (unsigned)v not running any task,
- * not handling interrupts, soon dead.
- * Called on the dying cpu, interrupts
- * are already disabled. Must not
- * sleep, must not fail */
#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug
* lock is dropped */
- #define CPU_STARTING 0x000A /* CPU (unsigned)v soon running.
- * Called on the new cpu, just before
- * enabling interrupts. Must not sleep,
- * must not fail */
#define CPU_BROKEN 0x000B /* CPU (unsigned)v did not die properly,
* perhaps due to preemption. */
#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN)
- #define CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN)
- #define CPU_STARTING_FROZEN (CPU_STARTING | CPU_TASKS_FROZEN)
-
#ifdef CONFIG_SMP
extern bool cpuhp_tasks_frozen;
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
-extern int disable_nonboot_cpus(void);
+extern int freeze_secondary_cpus(int primary);
+static inline int disable_nonboot_cpus(void)
+{
+ return freeze_secondary_cpus(0);
+}
extern void enable_nonboot_cpus(void);
#else /* !CONFIG_PM_SLEEP_SMP */
static inline int disable_nonboot_cpus(void) { return 0; }
#ifndef __CPUHOTPLUG_H
#define __CPUHOTPLUG_H
+#include <linux/types.h>
+
enum cpuhp_state {
CPUHP_OFFLINE,
CPUHP_CREATE_THREADS,
CPUHP_PERF_SUPERH,
CPUHP_X86_HPET_DEAD,
CPUHP_X86_APB_DEAD,
+ CPUHP_VIRT_NET_DEAD,
+ CPUHP_SLUB_DEAD,
+ CPUHP_MM_WRITEBACK_DEAD,
+ CPUHP_SOFTIRQ_DEAD,
+ CPUHP_NET_MVNETA_DEAD,
+ CPUHP_CPUIDLE_DEAD,
+ CPUHP_ARM64_FPSIMD_DEAD,
+ CPUHP_ARM_OMAP_WAKE_DEAD,
+ CPUHP_IRQ_POLL_DEAD,
+ CPUHP_BLOCK_SOFTIRQ_DEAD,
+ CPUHP_VIRT_SCSI_DEAD,
+ CPUHP_ACPI_CPUDRV_DEAD,
+ CPUHP_S390_PFAULT_DEAD,
+ CPUHP_BLK_MQ_DEAD,
CPUHP_WORKQUEUE_PREP,
CPUHP_POWER_NUMA_PREPARE,
CPUHP_HRTIMERS_PREPARE,
CPUHP_PROFILE_PREPARE,
CPUHP_X2APIC_PREPARE,
CPUHP_SMPCFD_PREPARE,
+ CPUHP_RELAY_PREPARE,
+ CPUHP_SLAB_PREPARE,
+ CPUHP_MD_RAID5_PREPARE,
CPUHP_RCUTREE_PREP,
+ CPUHP_CPUIDLE_COUPLED_PREPARE,
+ CPUHP_POWERPC_PMAC_PREPARE,
+ CPUHP_POWERPC_MMU_CTX_PREPARE,
CPUHP_NOTIFY_PREPARE,
+ CPUHP_ARM_SHMOBILE_SCU_PREPARE,
+ CPUHP_SH_SH3X_PREPARE,
+ CPUHP_BLK_MQ_PREPARE,
CPUHP_TIMERS_DEAD,
+ CPUHP_NOTF_ERR_INJ_PREPARE,
+ CPUHP_MIPS_SOC_PREPARE,
CPUHP_BRINGUP_CPU,
CPUHP_AP_IDLE_DEAD,
CPUHP_AP_OFFLINE,
CPUHP_AP_PERF_METAG_STARTING,
CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
CPUHP_AP_ARM_VFP_STARTING,
+ CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
+ CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
CPUHP_AP_PERF_ARM_STARTING,
CPUHP_AP_ARM_L2X0_STARTING,
CPUHP_AP_ARM_ARCH_TIMER_STARTING,
CPUHP_AP_ARM64_ISNDEP_STARTING,
CPUHP_AP_SMPCFD_DYING,
CPUHP_AP_X86_TBOOT_DYING,
- CPUHP_AP_NOTIFY_STARTING,
CPUHP_AP_ONLINE,
CPUHP_TEARDOWN_CPU,
CPUHP_AP_ONLINE_IDLE,
int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke,
int (*startup)(unsigned int cpu),
- int (*teardown)(unsigned int cpu));
+ int (*teardown)(unsigned int cpu), bool multi_instance);
/**
* cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
int (*startup)(unsigned int cpu),
int (*teardown)(unsigned int cpu))
{
- return __cpuhp_setup_state(state, name, true, startup, teardown);
+ return __cpuhp_setup_state(state, name, true, startup, teardown, false);
}
/**
int (*startup)(unsigned int cpu),
int (*teardown)(unsigned int cpu))
{
- return __cpuhp_setup_state(state, name, false, startup, teardown);
+ return __cpuhp_setup_state(state, name, false, startup, teardown,
+ false);
+ }
+
+ /**
+ * cpuhp_setup_state_multi - Add callbacks for multi state
+ * @state: The state for which the calls are installed
+ * @name: Name of the callback.
+ * @startup: startup callback function
+ * @teardown: teardown callback function
+ *
+ * Sets the internal multi_instance flag and prepares a state to work as a multi
+ * instance callback. No callbacks are invoked at this point. The callbacks are
+ * invoked once an instance for this state are registered via
+ * @cpuhp_state_add_instance or @cpuhp_state_add_instance_nocalls.
+ */
+ static inline int cpuhp_setup_state_multi(enum cpuhp_state state,
+ const char *name,
+ int (*startup)(unsigned int cpu,
+ struct hlist_node *node),
+ int (*teardown)(unsigned int cpu,
+ struct hlist_node *node))
+ {
+ return __cpuhp_setup_state(state, name, false,
+ (void *) startup,
+ (void *) teardown, true);
+ }
+
+ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+ bool invoke);
+
+ /**
+ * cpuhp_state_add_instance - Add an instance for a state and invoke startup
+ * callback.
+ * @state: The state for which the instance is installed
+ * @node: The node for this individual state.
+ *
+ * Installs the instance for the @state and invokes the startup callback on
+ * the present cpus which have already reached the @state. The @state must have
+ * been earlier marked as multi-instance by @cpuhp_setup_state_multi.
+ */
+ static inline int cpuhp_state_add_instance(enum cpuhp_state state,
+ struct hlist_node *node)
+ {
+ return __cpuhp_state_add_instance(state, node, true);
+ }
+
+ /**
+ * cpuhp_state_add_instance_nocalls - Add an instance for a state without
+ * invoking the startup callback.
+ * @state: The state for which the instance is installed
+ * @node: The node for this individual state.
+ *
+ * Installs the instance for the @state The @state must have been earlier
+ * marked as multi-instance by @cpuhp_setup_state_multi.
+ */
+ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
+ struct hlist_node *node)
+ {
+ return __cpuhp_state_add_instance(state, node, false);
}
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke);
__cpuhp_remove_state(state, false);
}
+ /**
+ * cpuhp_remove_multi_state - Remove hotplug multi state callback
+ * @state: The state for which the calls are removed
+ *
+ * Removes the callback functions from a multi state. This is the reverse of
+ * cpuhp_setup_state_multi(). All instances should have been removed before
+ * invoking this function.
+ */
+ static inline void cpuhp_remove_multi_state(enum cpuhp_state state)
+ {
+ __cpuhp_remove_state(state, false);
+ }
+
+ int __cpuhp_state_remove_instance(enum cpuhp_state state,
+ struct hlist_node *node, bool invoke);
+
+ /**
+ * cpuhp_state_remove_instance - Remove hotplug instance from state and invoke
+ * the teardown callback
+ * @state: The state from which the instance is removed
+ * @node: The node for this individual state.
+ *
+ * Removes the instance and invokes the teardown callback on the present cpus
+ * which have already reached the @state.
+ */
+ static inline int cpuhp_state_remove_instance(enum cpuhp_state state,
+ struct hlist_node *node)
+ {
+ return __cpuhp_state_remove_instance(state, node, true);
+ }
+
+ /**
+ * cpuhp_state_remove_instance_nocalls - Remove hotplug instance from state
+ * without invoking the reatdown callback
+ * @state: The state from which the instance is removed
+ * @node: The node for this individual state.
+ *
+ * Removes the instance without invoking the teardown callback.
+ */
+ static inline int cpuhp_state_remove_instance_nocalls(enum cpuhp_state state,
+ struct hlist_node *node)
+ {
+ return __cpuhp_state_remove_instance(state, node, false);
+ }
+
#ifdef CONFIG_SMP
void cpuhp_online_idle(enum cpuhp_state state);
#else
#include <linux/interrupt.h>
#include <linux/perf_event.h>
-
+#include <linux/sysfs.h>
#include <asm/cputype.h>
/*
struct arm_pmu *percpu_pmu;
};
+enum armpmu_attr_groups {
+ ARMPMU_ATTR_GROUP_COMMON,
+ ARMPMU_ATTR_GROUP_EVENTS,
+ ARMPMU_ATTR_GROUP_FORMATS,
+ ARMPMU_NR_ATTR_GROUPS
+};
+
struct arm_pmu {
struct pmu pmu;
cpumask_t active_irqs;
DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
struct platform_device *plat_device;
struct pmu_hw_events __percpu *hw_events;
- struct list_head entry;
+ struct hlist_node node;
struct notifier_block cpu_pm_nb;
+ /* the attr_groups array must be NULL-terminated */
+ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
};
#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
const struct of_device_id *of_table,
const struct pmu_probe_info *probe_table);
+#define ARMV8_PMU_PDEV_NAME "armv8-pmu"
+
#endif /* CONFIG_ARM_PMU */
#endif /* __ARM_PMU_H__ */
#include <linux/tick.h>
#include <linux/irq.h>
#include <linux/smpboot.h>
+ #include <linux/relay.h>
+ #include <linux/slab.h>
#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
* @thread: Pointer to the hotplug thread
* @should_run: Thread should execute
* @rollback: Perform a rollback
- * @cb_stat: The state for a single callback (install/uninstall)
- * @cb: Single callback function (install/uninstall)
+ * @single: Single callback invocation
+ * @bringup: Single callback bringup or teardown selector
+ * @cb_state: The state for a single callback (install/uninstall)
* @result: Result of the operation
* @done: Signal completion to the issuer of the task
*/
struct task_struct *thread;
bool should_run;
bool rollback;
+ bool single;
+ bool bringup;
+ struct hlist_node *node;
enum cpuhp_state cb_state;
- int (*cb)(unsigned int cpu);
int result;
struct completion done;
#endif
* @cant_stop: Bringup/teardown can't be stopped at this step
*/
struct cpuhp_step {
- const char *name;
- int (*startup)(unsigned int cpu);
- int (*teardown)(unsigned int cpu);
- bool skip_onerr;
- bool cant_stop;
+ const char *name;
+ union {
+ int (*single)(unsigned int cpu);
+ int (*multi)(unsigned int cpu,
+ struct hlist_node *node);
+ } startup;
+ union {
+ int (*single)(unsigned int cpu);
+ int (*multi)(unsigned int cpu,
+ struct hlist_node *node);
+ } teardown;
+ struct hlist_head list;
+ bool skip_onerr;
+ bool cant_stop;
+ bool multi_instance;
};
static DEFINE_MUTEX(cpuhp_state_mutex);
static struct cpuhp_step cpuhp_bp_states[];
static struct cpuhp_step cpuhp_ap_states[];
+ static bool cpuhp_is_ap_state(enum cpuhp_state state)
+ {
+ /*
+ * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
+ * purposes as that state is handled explicitly in cpu_down.
+ */
+ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
+ }
+
+ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
+ {
+ struct cpuhp_step *sp;
+
+ sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
+ return sp + state;
+ }
+
/**
* cpuhp_invoke_callback _ Invoke the callbacks for a given state
* @cpu: The cpu for which the callback should be invoked
* @step: The step in the state machine
- * @cb: The callback function to invoke
+ * @bringup: True if the bringup callback should be invoked
*
- * Called from cpu hotplug and from the state register machinery
+ * Called from cpu hotplug and from the state register machinery.
*/
- static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step,
- int (*cb)(unsigned int))
+ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
+ bool bringup, struct hlist_node *node)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
- int ret = 0;
-
- if (cb) {
- trace_cpuhp_enter(cpu, st->target, step, cb);
+ struct cpuhp_step *step = cpuhp_get_step(state);
+ int (*cbm)(unsigned int cpu, struct hlist_node *node);
+ int (*cb)(unsigned int cpu);
+ int ret, cnt;
+
+ if (!step->multi_instance) {
+ cb = bringup ? step->startup.single : step->teardown.single;
+ if (!cb)
+ return 0;
+ trace_cpuhp_enter(cpu, st->target, state, cb);
ret = cb(cpu);
- trace_cpuhp_exit(cpu, st->state, step, ret);
+ trace_cpuhp_exit(cpu, st->state, state, ret);
+ return ret;
+ }
+ cbm = bringup ? step->startup.multi : step->teardown.multi;
+ if (!cbm)
+ return 0;
+
+ /* Single invocation for instance add/remove */
+ if (node) {
+ trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+ ret = cbm(cpu, node);
+ trace_cpuhp_exit(cpu, st->state, state, ret);
+ return ret;
+ }
+
+ /* State transition. Invoke on all instances */
+ cnt = 0;
+ hlist_for_each(node, &step->list) {
+ trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+ ret = cbm(cpu, node);
+ trace_cpuhp_exit(cpu, st->state, state, ret);
+ if (ret)
+ goto err;
+ cnt++;
+ }
+ return 0;
+ err:
+ /* Rollback the instances if one failed */
+ cbm = !bringup ? step->startup.multi : step->teardown.multi;
+ if (!cbm)
+ return ret;
+
+ hlist_for_each(node, &step->list) {
+ if (!cnt--)
+ break;
+ cbm(cpu, node);
}
return ret;
}
}
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
+ static void __cpu_hotplug_enable(void)
+ {
+ if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
+ return;
+ cpu_hotplug_disabled--;
+ }
+
void cpu_hotplug_enable(void)
{
cpu_maps_update_begin();
- WARN_ON(--cpu_hotplug_disabled < 0);
+ __cpu_hotplug_enable();
cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
return 0;
}
- static int notify_starting(unsigned int cpu)
- {
- cpu_notify(CPU_STARTING, cpu);
- return 0;
- }
-
static int bringup_wait_for_ap(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
struct task_struct *idle = idle_thread_get(cpu);
int ret;
+ /*
+ * Some architectures have to walk the irq descriptors to
+ * setup the vector space for the cpu which comes online.
+ * Prevent irq alloc/free across the bringup.
+ */
+ irq_lock_sparse();
+
/* Arch-specific enabling code. */
ret = __cpu_up(cpu, idle);
+ irq_unlock_sparse();
if (ret) {
cpu_notify(CPU_UP_CANCELED, cpu);
return ret;
/*
* Hotplug state machine related functions
*/
- static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st,
- struct cpuhp_step *steps)
+ static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
{
for (st->state++; st->state < st->target; st->state++) {
- struct cpuhp_step *step = steps + st->state;
+ struct cpuhp_step *step = cpuhp_get_step(st->state);
if (!step->skip_onerr)
- cpuhp_invoke_callback(cpu, st->state, step->startup);
+ cpuhp_invoke_callback(cpu, st->state, true, NULL);
}
}
static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
- struct cpuhp_step *steps, enum cpuhp_state target)
+ enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
int ret = 0;
for (; st->state > target; st->state--) {
- struct cpuhp_step *step = steps + st->state;
-
- ret = cpuhp_invoke_callback(cpu, st->state, step->teardown);
+ ret = cpuhp_invoke_callback(cpu, st->state, false, NULL);
if (ret) {
st->target = prev_state;
- undo_cpu_down(cpu, st, steps);
+ undo_cpu_down(cpu, st);
break;
}
}
return ret;
}
- static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st,
- struct cpuhp_step *steps)
+ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
{
for (st->state--; st->state > st->target; st->state--) {
- struct cpuhp_step *step = steps + st->state;
+ struct cpuhp_step *step = cpuhp_get_step(st->state);
if (!step->skip_onerr)
- cpuhp_invoke_callback(cpu, st->state, step->teardown);
+ cpuhp_invoke_callback(cpu, st->state, false, NULL);
}
}
static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
- struct cpuhp_step *steps, enum cpuhp_state target)
+ enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
int ret = 0;
while (st->state < target) {
- struct cpuhp_step *step;
-
st->state++;
- step = steps + st->state;
- ret = cpuhp_invoke_callback(cpu, st->state, step->startup);
+ ret = cpuhp_invoke_callback(cpu, st->state, true, NULL);
if (ret) {
st->target = prev_state;
- undo_cpu_up(cpu, st, steps);
+ undo_cpu_up(cpu, st);
break;
}
}
{
enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
- return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target);
+ return cpuhp_down_callbacks(cpu, st, target);
}
/* Execute the online startup callbacks. Used to be CPU_ONLINE */
static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
{
- return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target);
+ return cpuhp_up_callbacks(cpu, st, st->target);
}
/*
st->should_run = false;
/* Single callback invocation for [un]install ? */
- if (st->cb) {
+ if (st->single) {
if (st->cb_state < CPUHP_AP_ONLINE) {
local_irq_disable();
- ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+ ret = cpuhp_invoke_callback(cpu, st->cb_state,
+ st->bringup, st->node);
local_irq_enable();
} else {
- ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+ ret = cpuhp_invoke_callback(cpu, st->cb_state,
+ st->bringup, st->node);
}
} else if (st->rollback) {
BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
- undo_cpu_down(cpu, st, cpuhp_ap_states);
+ undo_cpu_down(cpu, st);
/*
* This is a momentary workaround to keep the notifier users
* happy. Will go away once we got rid of the notifiers.
}
/* Invoke a single callback on a remote cpu */
- static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
- int (*cb)(unsigned int))
+ static int
+ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
+ struct hlist_node *node)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
* we invoke the thread function directly.
*/
if (!st->thread)
- return cpuhp_invoke_callback(cpu, state, cb);
+ return cpuhp_invoke_callback(cpu, state, bringup, node);
st->cb_state = state;
- st->cb = cb;
+ st->single = true;
+ st->bringup = bringup;
+ st->node = node;
+
/*
* Make sure the above stores are visible before should_run becomes
* true. Paired with the mb() above in cpuhp_thread_fun()
static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
{
st->result = 0;
- st->cb = NULL;
+ st->single = false;
/*
* Make sure the above stores are visible before should_run becomes
* true. Paired with the mb() above in cpuhp_thread_fun()
return err;
}
- static int notify_dying(unsigned int cpu)
- {
- cpu_notify(CPU_DYING, cpu);
- return 0;
- }
-
/* Take this CPU down. */
static int take_cpu_down(void *_param)
{
if (err < 0)
return err;
+ /*
+ * We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
+ * do this step again.
+ */
+ WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
+ st->state--;
/* Invoke the former CPU_DYING callbacks */
- for (; st->state > target; st->state--) {
- struct cpuhp_step *step = cpuhp_ap_states + st->state;
+ for (; st->state > target; st->state--)
+ cpuhp_invoke_callback(cpu, st->state, false, NULL);
- cpuhp_invoke_callback(cpu, st->state, step->teardown);
- }
/* Give up timekeeping duties */
tick_handover_do_timer();
/* Park the stopper thread */
BUG_ON(cpu_online(cpu));
/*
- * The migration_call() CPU_DYING callback will have removed all
+ * The CPUHP_AP_SCHED_MIGRATE_DYING callback will have removed all
* runnable tasks from the cpu, there's only the idle task left now
* that the migration thread is done doing the stop_machine thing.
*
#define notify_down_prepare NULL
#define takedown_cpu NULL
#define notify_dead NULL
- #define notify_dying NULL
#endif
#ifdef CONFIG_HOTPLUG_CPU
* The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
* to do the further cleanups.
*/
- ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+ ret = cpuhp_down_callbacks(cpu, st, target);
if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
st->target = prev_state;
st->rollback = true;
#endif /*CONFIG_HOTPLUG_CPU*/
/**
- * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
* @cpu: cpu that just started
*
- * This function calls the cpu_chain notifiers with CPU_STARTING.
* It must be called by the arch code on the new cpu, before the new cpu
* enables interrupts and before the "boot" cpu returns from __cpu_up().
*/
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
+ rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
while (st->state < target) {
- struct cpuhp_step *step;
-
st->state++;
- step = cpuhp_ap_states + st->state;
- cpuhp_invoke_callback(cpu, st->state, step->startup);
+ cpuhp_invoke_callback(cpu, st->state, true, NULL);
}
}
* responsible for bringing it up to the target state.
*/
target = min((int)target, CPUHP_BRINGUP_CPU);
- ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target);
+ ret = cpuhp_up_callbacks(cpu, st, target);
out:
cpu_hotplug_done();
return ret;
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
-int disable_nonboot_cpus(void)
+int freeze_secondary_cpus(int primary)
{
- int cpu, first_cpu, error = 0;
+ int cpu, error = 0;
cpu_maps_update_begin();
- first_cpu = cpumask_first(cpu_online_mask);
+ if (!cpu_online(primary))
+ primary = cpumask_first(cpu_online_mask);
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
pr_info("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
- if (cpu == first_cpu)
+ if (cpu == primary)
continue;
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
- WARN_ON(--cpu_hotplug_disabled < 0);
+ __cpu_hotplug_enable();
if (cpumask_empty(frozen_cpus))
goto out;
static struct cpuhp_step cpuhp_bp_states[] = {
[CPUHP_OFFLINE] = {
.name = "offline",
- .startup = NULL,
- .teardown = NULL,
+ .startup.single = NULL,
+ .teardown.single = NULL,
},
#ifdef CONFIG_SMP
[CPUHP_CREATE_THREADS]= {
- .name = "threads:create",
- .startup = smpboot_create_threads,
- .teardown = NULL,
+ .name = "threads:prepare",
+ .startup.single = smpboot_create_threads,
+ .teardown.single = NULL,
.cant_stop = true,
},
[CPUHP_PERF_PREPARE] = {
- .name = "perf prepare",
- .startup = perf_event_init_cpu,
- .teardown = perf_event_exit_cpu,
+ .name = "perf:prepare",
+ .startup.single = perf_event_init_cpu,
+ .teardown.single = perf_event_exit_cpu,
},
[CPUHP_WORKQUEUE_PREP] = {
- .name = "workqueue prepare",
- .startup = workqueue_prepare_cpu,
- .teardown = NULL,
+ .name = "workqueue:prepare",
+ .startup.single = workqueue_prepare_cpu,
+ .teardown.single = NULL,
},
[CPUHP_HRTIMERS_PREPARE] = {
- .name = "hrtimers prepare",
- .startup = hrtimers_prepare_cpu,
- .teardown = hrtimers_dead_cpu,
+ .name = "hrtimers:prepare",
+ .startup.single = hrtimers_prepare_cpu,
+ .teardown.single = hrtimers_dead_cpu,
},
[CPUHP_SMPCFD_PREPARE] = {
- .name = "SMPCFD prepare",
- .startup = smpcfd_prepare_cpu,
- .teardown = smpcfd_dead_cpu,
+ .name = "smpcfd:prepare",
+ .startup.single = smpcfd_prepare_cpu,
+ .teardown.single = smpcfd_dead_cpu,
+ },
+ [CPUHP_RELAY_PREPARE] = {
+ .name = "relay:prepare",
+ .startup.single = relay_prepare_cpu,
+ .teardown.single = NULL,
+ },
+ [CPUHP_SLAB_PREPARE] = {
+ .name = "slab:prepare",
+ .startup.single = slab_prepare_cpu,
+ .teardown.single = slab_dead_cpu,
},
[CPUHP_RCUTREE_PREP] = {
- .name = "RCU-tree prepare",
- .startup = rcutree_prepare_cpu,
- .teardown = rcutree_dead_cpu,
+ .name = "RCU/tree:prepare",
+ .startup.single = rcutree_prepare_cpu,
+ .teardown.single = rcutree_dead_cpu,
},
/*
* Preparatory and dead notifiers. Will be replaced once the notifiers
*/
[CPUHP_NOTIFY_PREPARE] = {
.name = "notify:prepare",
- .startup = notify_prepare,
- .teardown = notify_dead,
+ .startup.single = notify_prepare,
+ .teardown.single = notify_dead,
.skip_onerr = true,
.cant_stop = true,
},
* otherwise a RCU stall occurs.
*/
[CPUHP_TIMERS_DEAD] = {
- .name = "timers dead",
- .startup = NULL,
- .teardown = timers_dead_cpu,
+ .name = "timers:dead",
+ .startup.single = NULL,
+ .teardown.single = timers_dead_cpu,
},
/* Kicks the plugged cpu into life */
[CPUHP_BRINGUP_CPU] = {
.name = "cpu:bringup",
- .startup = bringup_cpu,
- .teardown = NULL,
+ .startup.single = bringup_cpu,
+ .teardown.single = NULL,
.cant_stop = true,
},
[CPUHP_AP_SMPCFD_DYING] = {
- .startup = NULL,
- .teardown = smpcfd_dying_cpu,
+ .name = "smpcfd:dying",
+ .startup.single = NULL,
+ .teardown.single = smpcfd_dying_cpu,
},
/*
* Handled on controll processor until the plugged processor manages
*/
[CPUHP_TEARDOWN_CPU] = {
.name = "cpu:teardown",
- .startup = NULL,
- .teardown = takedown_cpu,
+ .startup.single = NULL,
+ .teardown.single = takedown_cpu,
.cant_stop = true,
},
#else
/* First state is scheduler control. Interrupts are disabled */
[CPUHP_AP_SCHED_STARTING] = {
.name = "sched:starting",
- .startup = sched_cpu_starting,
- .teardown = sched_cpu_dying,
+ .startup.single = sched_cpu_starting,
+ .teardown.single = sched_cpu_dying,
},
[CPUHP_AP_RCUTREE_DYING] = {
- .startup = NULL,
- .teardown = rcutree_dying_cpu,
- },
- /*
- * Low level startup/teardown notifiers. Run with interrupts
- * disabled. Will be removed once the notifiers are converted to
- * states.
- */
- [CPUHP_AP_NOTIFY_STARTING] = {
- .name = "notify:starting",
- .startup = notify_starting,
- .teardown = notify_dying,
- .skip_onerr = true,
- .cant_stop = true,
+ .name = "RCU/tree:dying",
+ .startup.single = NULL,
+ .teardown.single = rcutree_dying_cpu,
},
/* Entry state on starting. Interrupts enabled from here on. Transient
* state for synchronsization */
},
/* Handle smpboot threads park/unpark */
[CPUHP_AP_SMPBOOT_THREADS] = {
- .name = "smpboot:threads",
- .startup = smpboot_unpark_threads,
- .teardown = NULL,
+ .name = "smpboot/threads:online",
+ .startup.single = smpboot_unpark_threads,
+ .teardown.single = NULL,
},
[CPUHP_AP_PERF_ONLINE] = {
- .name = "perf online",
- .startup = perf_event_init_cpu,
- .teardown = perf_event_exit_cpu,
+ .name = "perf:online",
+ .startup.single = perf_event_init_cpu,
+ .teardown.single = perf_event_exit_cpu,
},
[CPUHP_AP_WORKQUEUE_ONLINE] = {
- .name = "workqueue online",
- .startup = workqueue_online_cpu,
- .teardown = workqueue_offline_cpu,
+ .name = "workqueue:online",
+ .startup.single = workqueue_online_cpu,
+ .teardown.single = workqueue_offline_cpu,
},
[CPUHP_AP_RCUTREE_ONLINE] = {
- .name = "RCU-tree online",
- .startup = rcutree_online_cpu,
- .teardown = rcutree_offline_cpu,
+ .name = "RCU/tree:online",
+ .startup.single = rcutree_online_cpu,
+ .teardown.single = rcutree_offline_cpu,
},
/*
*/
[CPUHP_AP_NOTIFY_ONLINE] = {
.name = "notify:online",
- .startup = notify_online,
- .teardown = notify_down_prepare,
+ .startup.single = notify_online,
+ .teardown.single = notify_down_prepare,
.skip_onerr = true,
},
#endif
/* Last state is scheduler control setting the cpu active */
[CPUHP_AP_ACTIVE] = {
.name = "sched:active",
- .startup = sched_cpu_activate,
- .teardown = sched_cpu_deactivate,
+ .startup.single = sched_cpu_activate,
+ .teardown.single = sched_cpu_deactivate,
},
#endif
/* CPU is fully up and running. */
[CPUHP_ONLINE] = {
.name = "online",
- .startup = NULL,
- .teardown = NULL,
+ .startup.single = NULL,
+ .teardown.single = NULL,
},
};
return 0;
}
- static bool cpuhp_is_ap_state(enum cpuhp_state state)
- {
- /*
- * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
- * purposes as that state is handled explicitely in cpu_down.
- */
- return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
- }
-
- static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
- {
- struct cpuhp_step *sp;
-
- sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
- return sp + state;
- }
-
static void cpuhp_store_callbacks(enum cpuhp_state state,
const char *name,
int (*startup)(unsigned int cpu),
- int (*teardown)(unsigned int cpu))
+ int (*teardown)(unsigned int cpu),
+ bool multi_instance)
{
/* (Un)Install the callbacks for further cpu hotplug operations */
struct cpuhp_step *sp;
mutex_lock(&cpuhp_state_mutex);
sp = cpuhp_get_step(state);
- sp->startup = startup;
- sp->teardown = teardown;
+ sp->startup.single = startup;
+ sp->teardown.single = teardown;
sp->name = name;
+ sp->multi_instance = multi_instance;
+ INIT_HLIST_HEAD(&sp->list);
mutex_unlock(&cpuhp_state_mutex);
}
static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
{
- return cpuhp_get_step(state)->teardown;
+ return cpuhp_get_step(state)->teardown.single;
}
/*
* Call the startup/teardown function for a step either on the AP or
* on the current CPU.
*/
- static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
- int (*cb)(unsigned int), bool bringup)
+ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
+ struct hlist_node *node)
{
+ struct cpuhp_step *sp = cpuhp_get_step(state);
int ret;
- if (!cb)
+ if ((bringup && !sp->startup.single) ||
+ (!bringup && !sp->teardown.single))
return 0;
/*
* The non AP bound callbacks can fail on bringup. On teardown
*/
#ifdef CONFIG_SMP
if (cpuhp_is_ap_state(state))
- ret = cpuhp_invoke_ap_callback(cpu, state, cb);
+ ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
else
- ret = cpuhp_invoke_callback(cpu, state, cb);
+ ret = cpuhp_invoke_callback(cpu, state, bringup, node);
#else
- ret = cpuhp_invoke_callback(cpu, state, cb);
+ ret = cpuhp_invoke_callback(cpu, state, bringup, node);
#endif
BUG_ON(ret && !bringup);
return ret;
* Note: The teardown callbacks for rollback are not allowed to fail!
*/
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
- int (*teardown)(unsigned int cpu))
+ struct hlist_node *node)
{
int cpu;
- if (!teardown)
- return;
-
/* Roll back the already executed steps on the other cpus */
for_each_present_cpu(cpu) {
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
/* Did we invoke the startup call on that cpu ? */
if (cpustate >= state)
- cpuhp_issue_call(cpu, state, teardown, false);
+ cpuhp_issue_call(cpu, state, false, node);
}
}
return -ENOSPC;
}
+ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+ bool invoke)
+ {
+ struct cpuhp_step *sp;
+ int cpu;
+ int ret;
+
+ sp = cpuhp_get_step(state);
+ if (sp->multi_instance == false)
+ return -EINVAL;
+
+ get_online_cpus();
+
+ if (!invoke || !sp->startup.multi)
+ goto add_node;
+
+ /*
+ * Try to call the startup callback for each present cpu
+ * depending on the hotplug state of the cpu.
+ */
+ for_each_present_cpu(cpu) {
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+ int cpustate = st->state;
+
+ if (cpustate < state)
+ continue;
+
+ ret = cpuhp_issue_call(cpu, state, true, node);
+ if (ret) {
+ if (sp->teardown.multi)
+ cpuhp_rollback_install(cpu, state, node);
+ goto err;
+ }
+ }
+ add_node:
+ ret = 0;
+ mutex_lock(&cpuhp_state_mutex);
+ hlist_add_head(node, &sp->list);
+ mutex_unlock(&cpuhp_state_mutex);
+
+ err:
+ put_online_cpus();
+ return ret;
+ }
+ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
+
/**
* __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
* @state: The state to setup
int __cpuhp_setup_state(enum cpuhp_state state,
const char *name, bool invoke,
int (*startup)(unsigned int cpu),
- int (*teardown)(unsigned int cpu))
+ int (*teardown)(unsigned int cpu),
+ bool multi_instance)
{
int cpu, ret = 0;
int dyn_state = 0;
state = ret;
}
- cpuhp_store_callbacks(state, name, startup, teardown);
+ cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
if (!invoke || !startup)
goto out;
if (cpustate < state)
continue;
- ret = cpuhp_issue_call(cpu, state, startup, true);
+ ret = cpuhp_issue_call(cpu, state, true, NULL);
if (ret) {
- cpuhp_rollback_install(cpu, state, teardown);
- cpuhp_store_callbacks(state, NULL, NULL, NULL);
+ if (teardown)
+ cpuhp_rollback_install(cpu, state, NULL);
+ cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
goto out;
}
}
}
EXPORT_SYMBOL(__cpuhp_setup_state);
+ int __cpuhp_state_remove_instance(enum cpuhp_state state,
+ struct hlist_node *node, bool invoke)
+ {
+ struct cpuhp_step *sp = cpuhp_get_step(state);
+ int cpu;
+
+ BUG_ON(cpuhp_cb_check(state));
+
+ if (!sp->multi_instance)
+ return -EINVAL;
+
+ get_online_cpus();
+ if (!invoke || !cpuhp_get_teardown_cb(state))
+ goto remove;
+ /*
+ * Call the teardown callback for each present cpu depending
+ * on the hotplug state of the cpu. This function is not
+ * allowed to fail currently!
+ */
+ for_each_present_cpu(cpu) {
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+ int cpustate = st->state;
+
+ if (cpustate >= state)
+ cpuhp_issue_call(cpu, state, false, node);
+ }
+
+ remove:
+ mutex_lock(&cpuhp_state_mutex);
+ hlist_del(node);
+ mutex_unlock(&cpuhp_state_mutex);
+ put_online_cpus();
+
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
/**
* __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
* @state: The state to remove
*/
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
{
- int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state);
+ struct cpuhp_step *sp = cpuhp_get_step(state);
int cpu;
BUG_ON(cpuhp_cb_check(state));
get_online_cpus();
- if (!invoke || !teardown)
+ if (sp->multi_instance) {
+ WARN(!hlist_empty(&sp->list),
+ "Error: Removing state %d which has instances left.\n",
+ state);
+ goto remove;
+ }
+
+ if (!invoke || !cpuhp_get_teardown_cb(state))
goto remove;
/*
int cpustate = st->state;
if (cpustate >= state)
- cpuhp_issue_call(cpu, state, teardown, false);
+ cpuhp_issue_call(cpu, state, false, NULL);
}
remove:
- cpuhp_store_callbacks(state, NULL, NULL, NULL);
+ cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
put_online_cpus();
}
EXPORT_SYMBOL(__cpuhp_remove_state);
wake_up_process(tsk);
}
+/*
+ * If ksoftirqd is scheduled, we do not want to process pending softirqs
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ */
+static bool ksoftirqd_running(void)
+{
+ struct task_struct *tsk = __this_cpu_read(ksoftirqd);
+
+ return tsk && (tsk->state == TASK_RUNNING);
+}
+
/*
* preempt_count and SOFTIRQ_OFFSET usage:
* - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
pending = local_softirq_pending();
- if (pending)
+ if (pending && !ksoftirqd_running())
do_softirq_own_stack();
local_irq_restore(flags);
static inline void invoke_softirq(void)
{
+ if (ksoftirqd_running())
+ return;
+
if (!force_irqthreads) {
#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
/*
BUG();
}
- static void takeover_tasklets(unsigned int cpu)
+ static int takeover_tasklets(unsigned int cpu)
{
/* CPU is dead, so no lock needed. */
local_irq_disable();
raise_softirq_irqoff(HI_SOFTIRQ);
local_irq_enable();
+ return 0;
}
+ #else
+ #define takeover_tasklets NULL
#endif /* CONFIG_HOTPLUG_CPU */
- static int cpu_callback(struct notifier_block *nfb, unsigned long action,
- void *hcpu)
- {
- switch (action) {
- #ifdef CONFIG_HOTPLUG_CPU
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- takeover_tasklets((unsigned long)hcpu);
- break;
- #endif /* CONFIG_HOTPLUG_CPU */
- }
- return NOTIFY_OK;
- }
-
- static struct notifier_block cpu_nfb = {
- .notifier_call = cpu_callback
- };
-
static struct smp_hotplug_thread softirq_threads = {
.store = &ksoftirqd,
.thread_should_run = ksoftirqd_should_run,
static __init int spawn_ksoftirqd(void)
{
- register_cpu_notifier(&cpu_nfb);
-
+ cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL,
+ takeover_tasklets);
BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
return 0;