xtensa: SMP: fix secondary CPU initialization

- add missing memory barriers to the secondary CPU synchronization spin
  loops; add comment to the matching memory barrier in the boot_secondary
  and __cpu_die functions;
- use READ_ONCE/WRITE_ONCE to access cpu_start_id/cpu_start_ccount
  instead of reading/writing them directly;
- re-initialize cpu_running every time before starting secondary CPU to
  flush possible previous CPU startup results.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>

arch/xtensa/kernel/head.S

@@ -276,12 +276,13 @@ should_never_return:
 
 	movi	a2, cpu_start_ccount
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	movi	a3, 0
 	s32i	a3, a2, 0
-	memw
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	wsr	a3, ccount
@@ -317,11 +318,13 @@ ENTRY(cpu_restart)
 	rsr	a0, prid
 	neg	a2, a0
 	movi	a3, cpu_start_id
+	memw
 	s32i	a2, a3, 0
 #if XCHAL_DCACHE_IS_WRITEBACK
 	dhwbi	a3, 0
 #endif
 1:
+	memw
 	l32i	a2, a3, 0
 	dhi	a3, 0
 	bne	a2, a0, 1b

arch/xtensa/kernel/smp.c

@@ -195,9 +195,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 	int i;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpu_start_id = cpu;
-	system_flush_invalidate_dcache_range(
-			(unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+	WRITE_ONCE(cpu_start_id, cpu);
+	/* Pairs with the third memw in the cpu_restart */
+	mb();
+	system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+					     sizeof(cpu_start_id));
 #endif
 	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
 
@@ -206,18 +208,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 			ccount = get_ccount();
 		while (!ccount);
 
-		cpu_start_ccount = ccount;
+		WRITE_ONCE(cpu_start_ccount, ccount);
 
-		while (time_before(jiffies, timeout)) {
+		do {
+			/*
+			 * Pairs with the first two memws in the
+			 * .Lboot_secondary.
+			 */
 			mb();
-			if (!cpu_start_ccount)
-				break;
-		}
+			ccount = READ_ONCE(cpu_start_ccount);
+		} while (ccount && time_before(jiffies, timeout));
 
-		if (cpu_start_ccount) {
+		if (ccount) {
 			smp_call_function_single(0, mx_cpu_stop,
-					(void *)cpu, 1);
-			cpu_start_ccount = 0;
+						 (void *)cpu, 1);
+			WRITE_ONCE(cpu_start_ccount, 0);
 			return -EIO;
 		}
 	}
@@ -237,6 +242,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
 			__func__, cpu, idle, start_info.stack);
 
+	init_completion(&cpu_running);
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
 		wait_for_completion_timeout(&cpu_running,
@@ -298,8 +304,10 @@ void __cpu_die(unsigned int cpu)
 	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
 	while (time_before(jiffies, timeout)) {
 		system_invalidate_dcache_range((unsigned long)&cpu_start_id,
-				sizeof(cpu_start_id));
-		if (cpu_start_id == -cpu) {
+					       sizeof(cpu_start_id));
+		/* Pairs with the second memw in the cpu_restart */
+		mb();
+		if (READ_ONCE(cpu_start_id) == -cpu) {
 			platform_cpu_kill(cpu);
 			return;
 		}