#include <linux/smp.h>
#include <linux/cpu.h>
+#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
static struct {
struct list_head queue;
raw_spinlock_t lock;
case CPU_UP_PREPARE_FROZEN:
if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
cpu_to_node(cpu)))
- return NOTIFY_BAD;
+ return notifier_from_errno(-ENOMEM);
break;
#ifdef CONFIG_HOTPLUG_CPU
*/
list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
int refs;
+ void (*func) (void *info);
- if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
+ /*
+ * Since we walk the list without any locks, we might
+ * see an entry that was completed, removed from the
+ * list and is in the process of being reused.
+ *
+ * We must check that the cpu is in the cpumask before
+ * checking the refs, and both must be set before
+ * executing the callback on this cpu.
+ */
+
+ if (!cpumask_test_cpu(cpu, data->cpumask))
+ continue;
+
+ smp_rmb();
+
+ if (atomic_read(&data->refs) == 0)
continue;
+ func = data->csd.func; /* for later warn */
data->csd.func(data->csd.info);
+ /*
+ * If the cpu mask is not still set then it enabled interrupts,
+ * we took another smp interrupt, and executed the function
+ * twice on this cpu. In theory that copy decremented refs.
+ */
+ if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) {
+ WARN(1, "%pS enabled interrupts and double executed\n",
+ func);
+ continue;
+ }
+
refs = atomic_dec_return(&data->refs);
WARN_ON(refs < 0);
- if (!refs) {
- raw_spin_lock(&call_function.lock);
- list_del_rcu(&data->csd.list);
- raw_spin_unlock(&call_function.lock);
- }
if (refs)
continue;
+ WARN_ON(!cpumask_empty(data->cpumask));
+
+ raw_spin_lock(&call_function.lock);
+ list_del_rcu(&data->csd.list);
+ raw_spin_unlock(&call_function.lock);
+
csd_unlock(&data->csd);
}
*
* Returns 0 on success, else a negative status code.
*/
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
+int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
struct call_single_data d = {
* 3) any other online cpu in @mask
*/
int smp_call_function_any(const struct cpumask *mask,
- void (*func)(void *info), void *info, int wait)
+ smp_call_func_t func, void *info, int wait)
{
unsigned int cpu;
const struct cpumask *nodemask;
EXPORT_SYMBOL_GPL(smp_call_function_any);
/**
- * __smp_call_function_single(): Run a function on another CPU
+ * __smp_call_function_single(): Run a function on a specific CPU
* @cpu: The CPU to run on.
* @data: Pre-allocated and setup data structure
+ * @wait: If true, wait until function has completed on specified CPU.
*
* Like smp_call_function_single(), but allow caller to pass in a
* pre-allocated data structure. Useful for embedding @data inside
void __smp_call_function_single(int cpu, struct call_single_data *data,
int wait)
{
- csd_lock(data);
+ unsigned int this_cpu;
+ unsigned long flags;
+ this_cpu = get_cpu();
/*
* Can deadlock when called with interrupts disabled.
* We allow cpu's that are not yet online though, as no one else can
WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
&& !oops_in_progress);
- generic_exec_single(cpu, data, wait);
+ if (cpu == this_cpu) {
+ local_irq_save(flags);
+ data->func(data->info);
+ local_irq_restore(flags);
+ } else {
+ csd_lock(data);
+ generic_exec_single(cpu, data, wait);
+ }
+ put_cpu();
}
/**
* must be disabled when calling this function.
*/
void smp_call_function_many(const struct cpumask *mask,
- void (*func)(void *), void *info, bool wait)
+ smp_call_func_t func, void *info, bool wait)
{
struct call_function_data *data;
unsigned long flags;
- int cpu, next_cpu, this_cpu = smp_processor_id();
+ int refs, cpu, next_cpu, this_cpu = smp_processor_id();
/*
* Can deadlock when called with interrupts disabled.
* can't happen.
*/
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
- && !oops_in_progress);
+ && !oops_in_progress && !early_boot_irqs_disabled);
- /* So, what's a CPU they want? Ignoring this one. */
+ /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */
cpu = cpumask_first_and(mask, cpu_online_mask);
if (cpu == this_cpu)
cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
data = &__get_cpu_var(cfd_data);
csd_lock(&data->csd);
+ /* This BUG_ON verifies our reuse assertions and can be removed */
+ BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask));
+
+ /*
+ * The global call function queue list add and delete are protected
+ * by a lock, but the list is traversed without any lock, relying
+ * on the rcu list add and delete to allow safe concurrent traversal.
+ * We reuse the call function data without waiting for any grace
+ * period after some other cpu removes it from the global queue.
+ * This means a cpu might find our data block as it is being
+ * filled out.
+ *
+ * We hold off the interrupt handler on the other cpu by
+ * ordering our writes to the cpu mask vs our setting of the
+ * refs counter. We assert only the cpu owning the data block
+ * will set a bit in cpumask, and each bit will only be cleared
+ * by the subject cpu. Each cpu must first find its bit is
+ * set and then check that refs is set indicating the element is
+ * ready to be processed, otherwise it must skip the entry.
+ *
+ * On the previous iteration refs was set to 0 by another cpu.
+ * To avoid the use of transitivity, set the counter to 0 here
+ * so the wmb will pair with the rmb in the interrupt handler.
+ */
+ atomic_set(&data->refs, 0); /* convert 3rd to 1st party write */
+
data->csd.func = func;
data->csd.info = info;
+
+ /* Ensure 0 refs is visible before mask. Also orders func and info */
+ smp_wmb();
+
+ /* We rely on the "and" being processed before the store */
cpumask_and(data->cpumask, mask, cpu_online_mask);
cpumask_clear_cpu(this_cpu, data->cpumask);
- atomic_set(&data->refs, cpumask_weight(data->cpumask));
+ refs = cpumask_weight(data->cpumask);
+
+ /* Some callers race with other cpus changing the passed mask */
+ if (unlikely(!refs)) {
+ csd_unlock(&data->csd);
+ return;
+ }
raw_spin_lock_irqsave(&call_function.lock, flags);
/*
* will not miss any other list entries:
*/
list_add_rcu(&data->csd.list, &call_function.queue);
+ /*
+ * We rely on the wmb() in list_add_rcu to complete our writes
+ * to the cpumask before this write to refs, which indicates
+ * data is on the list and is ready to be processed.
+ */
+ atomic_set(&data->refs, refs);
raw_spin_unlock_irqrestore(&call_function.lock, flags);
/*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
-int smp_call_function(void (*func)(void *), void *info, int wait)
+int smp_call_function(smp_call_func_t func, void *info, int wait)
{
preempt_disable();
smp_call_function_many(cpu_online_mask, func, info, wait);
{
raw_spin_unlock_irq(&call_function.lock);
}
+#endif /* USE_GENERIC_SMP_HELPERS */
+
+/*
+ * Call a function on all processors. May be used during early boot while
+ * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead
+ * of local_irq_disable/enable().
+ */
+int on_each_cpu(void (*func) (void *info), void *info, int wait)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ preempt_disable();
+ ret = smp_call_function(func, info, wait);
+ local_irq_save(flags);
+ func(info);
+ local_irq_restore(flags);
+ preempt_enable();
+ return ret;
+}
+EXPORT_SYMBOL(on_each_cpu);