[PATCH v3 05/11] smp: replace smp_call_function_single_async with smp_call_csd

[Donghai Qiao <dqiao@redhat.com>]

Replaced smp_call_function_single_async with smp_call_csd and extended
it to support one CPU synchronous call with preallocated csd structure.

Signed-off-by: Donghai Qiao <dqiao@redhat.com>
---
v1 -> v2: removed 'x' from the function names and change XCALL to
	  SMP_CALL from the new macros
v2 -> v3: Changed the call of smp_call_private() to smp_call_csd()
 include/linux/smp.h |   3 +-
 kernel/smp.c        | 157 ++++++++++++++++++++------------------------
 2 files changed, 75 insertions(+), 85 deletions(-)

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 06a20454fd53..b4885e45690b 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -193,7 +193,8 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
 void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 			   void *info, bool wait, const struct cpumask *mask);
 
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd);
+#define	smp_call_function_single_async(cpu, csd) \
+	smp_call_csd(cpu, csd, SMP_CALL_TYPE_ASYNC)
 
 /*
  * Cpus stopping functions in panic. All have default weak definitions.
diff --git a/kernel/smp.c b/kernel/smp.c
index 8fdea9547502..f08135ad70e3 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -444,41 +444,6 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
 		send_call_function_single_ipi(cpu);
 }
 
-/*
- * Insert a previously allocated call_single_data_t element
- * for execution on the given CPU. data must already have
- * ->func, ->info, and ->flags set.
- */
-static int generic_exec_single(int cpu, struct __call_single_data *csd)
-{
-	if (cpu == smp_processor_id()) {
-		smp_call_func_t func = csd->func;
-		void *info = csd->info;
-		unsigned long flags;
-
-		/*
-		 * We can unlock early even for the synchronous on-stack case,
-		 * since we're doing this from the same CPU..
-		 */
-		csd_lock_record(csd);
-		csd_unlock(csd);
-		local_irq_save(flags);
-		func(info);
-		csd_lock_record(NULL);
-		local_irq_restore(flags);
-		return 0;
-	}
-
-	if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) {
-		csd_unlock(csd);
-		return -ENXIO;
-	}
-
-	__smp_call_single_queue(cpu, &csd->node.llist);
-
-	return 0;
-}
-
 /**
  * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks
  *
@@ -676,52 +641,6 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-/**
- * 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.
- *
- * If the function is called with one csd which has not yet been
- * processed by previous call to smp_call_function_single_async(), the
- * function will return immediately with -EBUSY showing that the csd
- * object is still in progress.
- *
- * NOTE: Be careful, there is unfortunately no current debugging facility to
- * validate the correctness of this serialization.
- *
- * Return: %0 on success or negative errno value on error
- */
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
-{
-	int err = 0;
-
-	preempt_disable();
-
-	if (csd->node.u_flags & CSD_FLAG_LOCK) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	csd->node.u_flags = CSD_FLAG_LOCK;
-	smp_wmb();
-
-	err = generic_exec_single(cpu, csd);
-
-out:
-	preempt_enable();
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(smp_call_function_single_async);
-
 /*
  * smp_call_function_any - Run a function on any of the given cpus
  * @mask: The mask of cpus it can run on.
@@ -1304,15 +1223,85 @@ EXPORT_SYMBOL(smp_call_mask_cond);
  * Because of that, this function can be used from the contexts with disabled
  * interrupts.
  *
- * Parameters
+ * The bit CSD_FLAG_LOCK will be set to csd->node.u_flags only if the call
+ * is made as type CSD_TYPE_SYNC or CSD_TYPE_ASYNC.
  *
+ * Parameters
  * cpu:   Must be a positive value less than nr_cpu_id.
  * csd:   The private csd provided by the callers.
- *
  * Others: see smp_call().
+ *
+ * Return: %0 on success or negative errno value on error.
+ *
+ * The following comments are from smp_call_function_single_async():
+ *
+ *   The call is asynchronous and can thus be done from contexts with
+ *   disabled interrupts. If the function is called with one csd which
+ *   has not yet been processed by previous call, the function will
+ *   return immediately with -EBUSY showing that the csd object is
+ *   still in progress.
+ *
+ *   NOTE: Be careful, there is unfortunately no current debugging
+ *   facility to validate the correctness of this serialization.
  */
 int smp_call_csd(int cpu, call_single_data_t *csd, unsigned int flags)
 {
-	return 0;
+	int err = 0;
+
+	if ((unsigned int)cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+		pr_warn("cpu ID must be a positive number < nr_cpu_ids and must be currently online\n");
+		return -EINVAL;
+	}
+
+	if (csd == NULL) {
+		pr_warn("csd must not be NULL\n");
+		return -EINVAL;
+	}
+
+	preempt_disable();
+	if (csd->node.u_flags & CSD_FLAG_LOCK) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	/*
+	 * CSD_FLAG_LOCK is set for CSD_TYPE_SYNC or CSD_TYPE_ASYNC only.
+	 */
+	if ((flags & ~(CSD_TYPE_SYNC | CSD_TYPE_ASYNC)) == 0)
+		csd->node.u_flags = CSD_FLAG_LOCK | flags;
+	else
+		csd->node.u_flags = flags;
+
+	if (cpu == smp_processor_id()) {
+		smp_call_func_t func = csd->func;
+		void *info = csd->info;
+		unsigned long flags;
+
+		/*
+		 * We can unlock early even for the synchronous on-stack case,
+		 * since we're doing this from the same CPU..
+		 */
+		csd_lock_record(csd);
+		csd_unlock(csd);
+		local_irq_save(flags);
+		func(info);
+		csd_lock_record(NULL);
+		local_irq_restore(flags);
+		goto out;
+	}
+
+	/*
+	 * Ensure the flags are visible before the csd
+	 * goes to the queue.
+	 */
+	smp_wmb();
+
+	__smp_call_single_queue(cpu, &csd->node.llist);
+
+	if (flags & CSD_TYPE_SYNC)
+		csd_lock_wait(csd);
+out:
+	preempt_enable();
+	return err;
 }
 EXPORT_SYMBOL(smp_call_csd);
-- 
2.27.0