s390: preempt: Fix preempt_count initialization

commit 6a942f5 upstream.

S390's init_idle_preempt_count(p, cpu) doesn't actually let us initialize the
preempt_count of the requested CPU's idle task: it unconditionally writes
to the current CPU's. This clearly conflicts with idle_threads_init(),
which intends to initialize *all* the idle tasks, including their
preempt_count (or their CPU's, if the arch uses a per-CPU preempt_count).

Unfortunately, it seems the way s390 does things doesn't let us initialize
every possible CPU's preempt_count early on, as the pages where this
resides are only allocated when a CPU is brought up and are freed when it
is brought down.

Let the arch-specific code set a CPU's preempt_count when its lowcore is
allocated, and turn init_idle_preempt_count() into an empty stub.

Fixes: f1a0a37 ("sched/core: Initialize the idle task with preemption disabled")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/20210707163338.1623014-1-valentin.schneider@arm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: Valentin Schneider

arch/s390/include/asm/preempt.h

@@ -29,12 +29,6 @@ static inline void preempt_count_set(int pc)
 				  old, new) != old);
 }
 
-#define init_task_preempt_count(p)	do { } while (0)
-
-#define init_idle_preempt_count(p, cpu)	do { \
-	S390_lowcore.preempt_count = PREEMPT_DISABLED; \
-} while (0)
-
 static inline void set_preempt_need_resched(void)
 {
 	__atomic_and(~PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
@@ -88,12 +82,6 @@ static inline void preempt_count_set(int pc)
 	S390_lowcore.preempt_count = pc;
 }
 
-#define init_task_preempt_count(p)	do { } while (0)
-
-#define init_idle_preempt_count(p, cpu)	do { \
-	S390_lowcore.preempt_count = PREEMPT_DISABLED; \
-} while (0)
-
 static inline void set_preempt_need_resched(void)
 {
 }
@@ -130,6 +118,10 @@ static inline bool should_resched(int preempt_offset)
 
 #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
+#define init_task_preempt_count(p)	do { } while (0)
+/* Deferred to CPU bringup time */
+#define init_idle_preempt_count(p, cpu)	do { } while (0)
+
 #ifdef CONFIG_PREEMPTION
 extern asmlinkage void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()

arch/s390/kernel/setup.c

@@ -454,6 +454,7 @@ static void __init setup_lowcore_dat_off(void)
 	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
 	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
+	lc->preempt_count = PREEMPT_DISABLED;
 
 	set_prefix((u32)(unsigned long) lc);
 	lowcore_ptr[0] = lc;

arch/s390/kernel/smp.c

@@ -215,6 +215,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 	lc->br_r1_trampoline = 0x07f1;	/* br %r1 */
 	lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
 	lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
+	lc->preempt_count = PREEMPT_DISABLED;
 	if (nmi_alloc_per_cpu(lc))
 		goto out_async;
 	if (vdso_alloc_per_cpu(lc))