riscv: misaligned: use on_each_cpu() for scalar misaligned access probing

schedule_on_each_cpu() was used without any good reason while documented
as very slow. This call was in the boot path, so better use
on_each_cpu() for scalar misaligned checking. Vector misaligned check
still needs to use schedule_on_each_cpu() since it requires irqs to be
enabled but that's less of a problem since this code is ran in a kthread.
Add a comment to explicit that.

Signed-off-by: Clément Léger <[email protected]>
Reviewed-by: Andrew Jones <[email protected]>
Reviewed-by: Charlie Jenkins <[email protected]>
Tested-by: Charlie Jenkins <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: clementleger

arch/riscv/kernel/traps_misaligned.c

@@ -627,6 +627,10 @@ bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 {
 	int cpu;
 
+	/*
+	 * While being documented as very slow, schedule_on_each_cpu() is used since
+	 * kernel_vector_begin() expects irqs to be enabled or it will panic()
+	 */
 	schedule_on_each_cpu(check_vector_unaligned_access_emulated);
 
 	for_each_online_cpu(cpu)
@@ -647,7 +651,7 @@ bool __init check_vector_unaligned_access_emulated_all_cpus(void)
 
 static bool unaligned_ctl __read_mostly;
 
-static void check_unaligned_access_emulated(struct work_struct *work __always_unused)
+static void check_unaligned_access_emulated(void *arg __always_unused)
 {
 	int cpu = smp_processor_id();
 	long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
@@ -688,7 +692,7 @@ bool __init check_unaligned_access_emulated_all_cpus(void)
 	 * accesses emulated since tasks requesting such control can run on any
 	 * CPU.
 	 */
-	schedule_on_each_cpu(check_unaligned_access_emulated);
+	on_each_cpu(check_unaligned_access_emulated, NULL, 1);
 
 	for_each_online_cpu(cpu)
 		if (per_cpu(misaligned_access_speed, cpu)