smp: Change function signatures to use call_single_data_t

call_single_data_t is a size-aligned typedef of struct __call_single_data.

This alignment is desirable in order to have smp_call_function*() avoid
bouncing an extra cacheline in case of an unaligned csd, given this
would hurt performance.

Since the removal of struct request->csd in commit 660e802c76c8
("blk-mq: use percpu csd to remote complete instead of per-rq csd") there
are no current users of smp_call_function*() with unaligned csd.

Change every 'struct __call_single_data' function parameter to
'call_single_data_t', so we have warnings if any new code tries to
introduce an smp_call_function*() call with unaligned csd.

Signed-off-by: Leonardo Bras <[e-mail]>
Reviewed-by: Guo Ren <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

include/linux/smp.h

···
 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);
+int smp_call_function_single_async(int cpu, call_single_data_t *csd);
 
 /*
  * Cpus stopping functions in panic. All have default weak definitions.

include/trace/events/csd.h

···
 	TP_PROTO(const unsigned int cpu,
 		unsigned long callsite,
 		smp_call_func_t func,
-		struct __call_single_data *csd),
+		call_single_data_t *csd),
 
 	TP_ARGS(cpu, callsite, func, csd),
 
···
  */
 DECLARE_EVENT_CLASS(csd_function,
 
-	TP_PROTO(smp_call_func_t func, struct __call_single_data *csd),
+	TP_PROTO(smp_call_func_t func, call_single_data_t *csd),
 
 	TP_ARGS(func, csd),
 
···
 );
 
 DEFINE_EVENT(csd_function, csd_function_entry,
-	TP_PROTO(smp_call_func_t func, struct __call_single_data *csd),
+	TP_PROTO(smp_call_func_t func, call_single_data_t *csd),
 	TP_ARGS(func, csd)
 );
 
 DEFINE_EVENT(csd_function, csd_function_exit,
-	TP_PROTO(smp_call_func_t func, struct __call_single_data *csd),
+	TP_PROTO(smp_call_func_t func, call_single_data_t *csd),
 	TP_ARGS(func, csd)
 );
 

kernel/smp.c

···
 }
 
 static __always_inline void
-csd_do_func(smp_call_func_t func, void *info, struct __call_single_data *csd)
+csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd)
 {
 	trace_csd_function_entry(func, csd);
 	func(info);
···
 static atomic_t csd_bug_count = ATOMIC_INIT(0);
 
 /* Record current CSD work for current CPU, NULL to erase. */
-static void __csd_lock_record(struct __call_single_data *csd)
+static void __csd_lock_record(call_single_data_t *csd)
 {
 	if (!csd) {
 		smp_mb(); /* NULL cur_csd after unlock. */
···
 		  /* Or before unlock, as the case may be. */
 }
 
-static __always_inline void csd_lock_record(struct __call_single_data *csd)
+static __always_inline void csd_lock_record(call_single_data_t *csd)
 {
 	if (static_branch_unlikely(&csdlock_debug_enabled))
 		__csd_lock_record(csd);
 }
 
-static int csd_lock_wait_getcpu(struct __call_single_data *csd)
+static int csd_lock_wait_getcpu(call_single_data_t *csd)
 {
 	unsigned int csd_type;
 
···
  * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
  * so waiting on other types gets much less information.
  */
-static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *ts1, int *bug_id)
+static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id)
 {
 	int cpu = -1;
 	int cpux;
···
  * previous function call. For multi-cpu calls its even more interesting
  * as we'll have to ensure no other cpu is observing our csd.
  */
-static void __csd_lock_wait(struct __call_single_data *csd)
+static void __csd_lock_wait(call_single_data_t *csd)
 {
 	int bug_id = 0;
 	u64 ts0, ts1;
···
 	smp_acquire__after_ctrl_dep();
 }
 
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
 {
 	if (static_branch_unlikely(&csdlock_debug_enabled)) {
 		__csd_lock_wait(csd);
···
 	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #else
-static void csd_lock_record(struct __call_single_data *csd)
+static void csd_lock_record(call_single_data_t *csd)
 {
 }
 
-static __always_inline void csd_lock_wait(struct __call_single_data *csd)
+static __always_inline void csd_lock_wait(call_single_data_t *csd)
 {
 	smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK));
 }
 #endif
 
-static __always_inline void csd_lock(struct __call_single_data *csd)
+static __always_inline void csd_lock(call_single_data_t *csd)
 {
 	csd_lock_wait(csd);
 	csd->node.u_flags |= CSD_FLAG_LOCK;
···
 	smp_wmb();
 }
 
-static __always_inline void csd_unlock(struct __call_single_data *csd)
+static __always_inline void csd_unlock(call_single_data_t *csd)
 {
 	WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK));
 
···
  * 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)
+static int generic_exec_single(int cpu, call_single_data_t *csd)
 {
 	if (cpu == smp_processor_id()) {
 		smp_call_func_t func = csd->func;
···
  *
  * Return: %0 on success or negative errno value on error
  */
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
+int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 {
 	int err = 0;
 

kernel/up.c

···
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
+int smp_call_function_single_async(int cpu, call_single_data_t *csd)
 {
 	unsigned long flags;