smp: fix smp_call_function_single_async prototype

As of commit 966a967 ("smp: Avoid using two cache lines for struct
call_single_data"), the smp code prefers 32-byte aligned call_single_data
objects for performance reasons, but the block layer includes an instance
of this structure in the main 'struct request' that is more senstive
to size than to performance here, see 4ccafe0 ("block: unalign
call_single_data in struct request").

The result is a violation of the calling conventions that clang correctly
points out:

block/blk-mq.c:630:39: warning: passing 8-byte aligned argument to 32-byte aligned parameter 2 of 'smp_call_function_single_async' may result in an unaligned pointer access [-Walign-mismatch]
                smp_call_function_single_async(cpu, &rq->csd);

It does seem that the usage of the call_single_data without cache line
alignment should still be allowed by the smp code, so just change the
function prototype so it accepts both, but leave the default alignment
unchanged for the other users. This seems better to me than adding
a local hack to shut up an otherwise correct warning in the caller.

Link: https://lore.kernel.org/linux-block/20210330230249.709221-1-jiancai@google.com/
Link: ClangBuiltLinux#1328
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jian Cai <jiancai@google.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>

include/linux/smp.h

@@ -53,7 +53,7 @@ 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, call_single_data_t *csd);
+int smp_call_function_single_async(int cpu, struct __call_single_data *csd);
 
 /*
  * Cpus stopping functions in panic. All have default weak definitions.

kernel/smp.c

@@ -401,7 +401,7 @@ static void __csd_lock_wait(call_single_data_t *csd)
 	smp_acquire__after_ctrl_dep();
 }
 
-static __always_inline void csd_lock_wait(call_single_data_t *csd)
+static __always_inline void csd_lock_wait(struct __call_single_data *csd)
 {
 	if (static_branch_unlikely(&csdlock_debug_enabled)) {
 		__csd_lock_wait(csd);
@@ -501,7 +501,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node)
  * for execution on the given CPU. data must already have
  * ->func, ->info, and ->flags set.
  */
-static int generic_exec_single(int cpu, call_single_data_t *csd)
+static int generic_exec_single(int cpu, struct __call_single_data *csd)
 {
 	if (cpu == smp_processor_id()) {
 		smp_call_func_t func = csd->func;
@@ -784,7 +784,7 @@ EXPORT_SYMBOL(smp_call_function_single);
  * 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, call_single_data_t *csd)
+int smp_call_function_single_async(int cpu, struct __call_single_data *csd)
 {
 	int err = 0;