1 files changed, 71 insertions, 120 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index bd9f94028838..06d574e42c72 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -23,17 +23,11 @@ enum {
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
-	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
 
-struct call_single_queue {
-	struct list_head	list;
-	raw_spinlock_t		lock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -47,14 +41,8 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				cpu_to_node(cpu)))
 			return notifier_from_errno(-ENOMEM);
-		if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
-				cpu_to_node(cpu))) {
-			free_cpumask_var(cfd->cpumask);
-			return notifier_from_errno(-ENOMEM);
-		}
 		cfd->csd = alloc_percpu(struct call_single_data);
 		if (!cfd->csd) {
-			free_cpumask_var(cfd->cpumask_ipi);
 			free_cpumask_var(cfd->cpumask);
 			return notifier_from_errno(-ENOMEM);
 		}
@@ -67,7 +55,6 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
-		free_cpumask_var(cfd->cpumask_ipi);
 		free_percpu(cfd->csd);
 		break;
 #endif
@@ -85,12 +72,8 @@ void __init call_function_init(void)
 	void *cpu = (void *)(long)smp_processor_id();
 	int i;
 
-	for_each_possible_cpu(i) {
-		struct call_single_queue *q = &per_cpu(call_single_queue, i);
-
-		raw_spin_lock_init(&q->lock);
-		INIT_LIST_HEAD(&q->list);
-	}
+	for_each_possible_cpu(i)
+		init_llist_head(&per_cpu(call_single_queue, i));
 
 	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
 	register_cpu_notifier(&hotplug_cfd_notifier);
@@ -134,25 +117,46 @@ static void csd_unlock(struct call_single_data *csd)
 	csd->flags &= ~CSD_FLAG_LOCK;
 }
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
+
 /*
  * Insert a previously allocated call_single_data element
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
+static int generic_exec_single(int cpu, struct call_single_data *csd,
+			       smp_call_func_t func, void *info, int wait)
 {
-	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
+	struct call_single_data csd_stack = { .flags = 0 };
 	unsigned long flags;
-	int ipi;
+
+
+	if (cpu == smp_processor_id()) {
+		local_irq_save(flags);
+		func(info);
+		local_irq_restore(flags);
+		return 0;
+	}
+
+
+	if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
+		return -ENXIO;
+
+
+	if (!csd) {
+		csd = &csd_stack;
+		if (!wait)
+			csd = &__get_cpu_var(csd_data);
+	}
+
+	csd_lock(csd);
+
+	csd->func = func;
+	csd->info = info;
 
 	if (wait)
 		csd->flags |= CSD_FLAG_WAIT;
 
-	raw_spin_lock_irqsave(&dst->lock, flags);
-	ipi = list_empty(&dst->list);
-	list_add_tail(&csd->list, &dst->list);
-	raw_spin_unlock_irqrestore(&dst->lock, flags);
-
 	/*
 	 * The list addition should be visible before sending the IPI
 	 * handler locks the list to pull the entry off it because of
@@ -164,11 +168,13 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
 	 * locking and barrier primitives. Generic code isn't really
 	 * equipped to do the right thing...
 	 */
-	if (ipi)
+	if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
 		arch_send_call_function_single_ipi(cpu);
 
 	if (wait)
 		csd_lock_wait(csd);
+
+	return 0;
 }
 
 /*
@@ -177,32 +183,23 @@ static void generic_exec_single(int cpu, struct call_single_data *csd, int wait)
  */
 void generic_smp_call_function_single_interrupt(void)
 {
-	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
-	LIST_HEAD(list);
+	struct llist_node *entry;
+	struct call_single_data *csd, *csd_next;
 
 	/*
 	 * Shouldn't receive this interrupt on a cpu that is not yet online.
 	 */
 	WARN_ON_ONCE(!cpu_online(smp_processor_id()));
 
-	raw_spin_lock(&q->lock);
-	list_replace_init(&q->list, &list);
-	raw_spin_unlock(&q->lock);
-
-	while (!list_empty(&list)) {
-		struct call_single_data *csd;
-
-		csd = list_entry(list.next, struct call_single_data, list);
-		list_del(&csd->list);
+	entry = llist_del_all(&__get_cpu_var(call_single_queue));
+	entry = llist_reverse_order(entry);
 
+	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
 		csd->func(csd->info);
-
 		csd_unlock(csd);
 	}
 }
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
-
 /*
  * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
@@ -214,12 +211,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
 int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 			     int wait)
 {
-	struct call_single_data d = {
-		.flags = 0,
-	};
-	unsigned long flags;
 	int this_cpu;
-	int err = 0;
+	int err;
 
 	/*
 	 * prevent preemption and reschedule on another processor,
@@ -236,32 +229,41 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 	WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
 		     && !oops_in_progress);
 
-	if (cpu == this_cpu) {
-		local_irq_save(flags);
-		func(info);
-		local_irq_restore(flags);
-	} else {
-		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-			struct call_single_data *csd = &d;
+	err = generic_exec_single(cpu, NULL, func, info, wait);
 
-			if (!wait)
-				csd = &__get_cpu_var(csd_data);
+	put_cpu();
 
-			csd_lock(csd);
+	return err;
+}
+EXPORT_SYMBOL(smp_call_function_single);
 
-			csd->func = func;
-			csd->info = info;
-			generic_exec_single(cpu, csd, wait);
-		} else {
-			err = -ENXIO;	/* CPU not online */
-		}
-	}
+/**
+ * smp_call_function_single_async(): Run an asynchronous function on a
+ * 			         specific CPU.
+ * @cpu: The CPU to run on.
+ * @csd: Pre-allocated and setup data structure
+ *
+ * Like smp_call_function_single(), but the call is asynchonous and
+ * can thus be done from contexts with disabled interrupts.
+ *
+ * The caller passes his own pre-allocated data structure
+ * (ie: embedded in an object) and is responsible for synchronizing it
+ * such that the IPIs performed on the @csd are strictly serialized.
+ *
+ * NOTE: Be careful, there is unfortunately no current debugging facility to
+ * validate the correctness of this serialization.
+ */
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
+{
+	int err = 0;
 
-	put_cpu();
+	preempt_disable();
+	err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+	preempt_enable();
 
 	return err;
 }
-EXPORT_SYMBOL(smp_call_function_single);
+EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /*
  * smp_call_function_any - Run a function on any of the given cpus
@@ -307,44 +309,6 @@ call:
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
 /**
- * __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
- * other structures, for instance.
- */
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-				int wait)
-{
-	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
-	 * send smp call function interrupt to this cpu and as such deadlocks
-	 * can't happen.
-	 */
-	WARN_ON_ONCE(cpu_online(smp_processor_id()) && wait && irqs_disabled()
-		     && !oops_in_progress);
-
-	if (cpu == this_cpu) {
-		local_irq_save(flags);
-		csd->func(csd->info);
-		local_irq_restore(flags);
-	} else {
-		csd_lock(csd);
-		generic_exec_single(cpu, csd, wait);
-	}
-	put_cpu();
-}
-EXPORT_SYMBOL_GPL(__smp_call_function_single);
-
-/**
  * smp_call_function_many(): Run a function on a set of other CPUs.
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
@@ -402,30 +366,17 @@ void smp_call_function_many(const struct cpumask *mask,
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
-	/*
-	 * After we put an entry into the list, cfd->cpumask may be cleared
-	 * again when another CPU sends another IPI for a SMP function call, so
-	 * cfd->cpumask will be zero.
-	 */
-	cpumask_copy(cfd->cpumask_ipi, cfd->cpumask);
-
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
-		struct call_single_queue *dst =
-					&per_cpu(call_single_queue, cpu);
-		unsigned long flags;
 
 		csd_lock(csd);
 		csd->func = func;
 		csd->info = info;
-
-		raw_spin_lock_irqsave(&dst->lock, flags);
-		list_add_tail(&csd->list, &dst->list);
-		raw_spin_unlock_irqrestore(&dst->lock, flags);
+		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
+	arch_send_call_function_ipi_mask(cfd->cpumask);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {