posix-timers: thread posix-cpu-timers on -rt

posix-cpu-timer code takes non -rt safe locks in hard irq
context. Move it to a thread.

[ 3.0 fixes from Peter Zijlstra <peterz@infradead.org> ]

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/init_task.h

@@ -145,6 +145,12 @@ extern struct task_group root_task_group;
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define INIT_TIMER_LIST		.posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
 	.vtime_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.vtime_lock),	\
@@ -218,6 +224,7 @@ extern struct task_group root_task_group;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock),	\
 	.timer_slack_ns = 50000, /* 50 usec default slack */		\
+	INIT_TIMER_LIST							\
 	.pids = {							\
 		[PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),		\
 		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\

include/linux/sched.h

@@ -1317,6 +1317,9 @@ struct task_struct {
 
 	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct *posix_timer_list;
+#endif
 
 /* process credentials */
 	const struct cred __rcu *real_cred; /* objective and real subjective task

init/main.c

@@ -6,7 +6,7 @@
  *  GK 2/5/95  -  Changed to support mounting root fs via NFS
  *  Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
  *  Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
- *  Simplified starting of init:  Michael A. Griffith <grif@acm.org> 
+ *  Simplified starting of init:  Michael A. Griffith <grif@acm.org>
  */
 
 #define DEBUG		/* Enable initcall_debug */
@@ -74,6 +74,7 @@
 #include <linux/ptrace.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/posix-timers.h>
 #include <linux/sched_clock.h>
 #include <linux/context_tracking.h>
 #include <linux/random.h>

kernel/fork.c

@@ -1114,6 +1114,9 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	tsk->posix_timer_list = NULL;
+#endif
 	tsk->cputime_expires.prof_exp = 0;
 	tsk->cputime_expires.virt_exp = 0;
 	tsk->cputime_expires.sched_exp = 0;

kernel/posix-cpu-timers.c

@@ -3,6 +3,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/sched/rt.h>
 #include <linux/posix-timers.h>
 #include <linux/errno.h>
 #include <linux/math64.h>
@@ -640,7 +641,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
+	WARN_ON_ONCE_NONRT(!irqs_disabled());
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
@@ -1061,7 +1062,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
+	WARN_ON_ONCE_NONRT(!irqs_disabled());
 	arm_timer(timer);
 	unlock_task_sighand(p, &flags);
 
@@ -1127,10 +1128,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	sig = tsk->signal;
 	if (sig->cputimer.running) {
 		struct task_cputime group_sample;
+		unsigned long flags;
 
-		raw_spin_lock(&sig->cputimer.lock);
+		raw_spin_lock_irqsave(&sig->cputimer.lock, flags);
 		group_sample = sig->cputimer.cputime;
-		raw_spin_unlock(&sig->cputimer.lock);
+		raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags);
 
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
@@ -1144,13 +1146,13 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
  * already updated our counts.  We need to check if any timers fire now.
  * Interrupts are disabled.
  */
-void run_posix_cpu_timers(struct task_struct *tsk)
+static void __run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	WARN_ON_ONCE(!irqs_disabled());
+	WARN_ON_ONCE_NONRT(!irqs_disabled());
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1208,6 +1210,175 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	}
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
+
+static int posix_cpu_timers_thread(void *data)
+{
+	int cpu = (long)data;
+
+	BUG_ON(per_cpu(posix_timer_task,cpu) != current);
+
+	while (!kthread_should_stop()) {
+		struct task_struct *tsk = NULL;
+		struct task_struct *next = NULL;
+
+		if (cpu_is_offline(cpu))
+			goto wait_to_die;
+
+		/* grab task list */
+		raw_local_irq_disable();
+		tsk = per_cpu(posix_timer_tasklist, cpu);
+		per_cpu(posix_timer_tasklist, cpu) = NULL;
+		raw_local_irq_enable();
+
+		/* its possible the list is empty, just return */
+		if (!tsk) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+			__set_current_state(TASK_RUNNING);
+			continue;
+		}
+
+		/* Process task list */
+		while (1) {
+			/* save next */
+			next = tsk->posix_timer_list;
+
+			/* run the task timers, clear its ptr and
+			 * unreference it
+			 */
+			__run_posix_cpu_timers(tsk);
+			tsk->posix_timer_list = NULL;
+			put_task_struct(tsk);
+
+			/* check if this is the last on the list */
+			if (next == tsk)
+				break;
+			tsk = next;
+		}
+	}
+	return 0;
+
+wait_to_die:
+	/* Wait for kthread_stop */
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	unsigned long cpu = smp_processor_id();
+	struct task_struct *tasklist;
+
+	BUG_ON(!irqs_disabled());
+	if(!per_cpu(posix_timer_task, cpu))
+		return;
+	/* get per-cpu references */
+	tasklist = per_cpu(posix_timer_tasklist, cpu);
+
+	/* check to see if we're already queued */
+	if (!tsk->posix_timer_list) {
+		get_task_struct(tsk);
+		if (tasklist) {
+			tsk->posix_timer_list = tasklist;
+		} else {
+			/*
+			 * The list is terminated by a self-pointing
+			 * task_struct
+			 */
+			tsk->posix_timer_list = tsk;
+		}
+		per_cpu(posix_timer_tasklist, cpu) = tsk;
+	}
+	/* XXX signal the thread somehow */
+	wake_up_process(per_cpu(posix_timer_task, cpu));
+}
+
+/*
+ * posix_cpu_thread_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+static int posix_cpu_thread_call(struct notifier_block *nfb,
+				 unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	struct task_struct *p;
+	struct sched_param param;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		p = kthread_create(posix_cpu_timers_thread, hcpu,
+					"posix_cpu_timers/%d",cpu);
+		if (IS_ERR(p))
+			return NOTIFY_BAD;
+		p->flags |= PF_NOFREEZE;
+		kthread_bind(p, cpu);
+		/* Must be high prio to avoid getting starved */
+		param.sched_priority = MAX_RT_PRIO-1;
+		sched_setscheduler(p, SCHED_FIFO, &param);
+		per_cpu(posix_timer_task,cpu) = p;
+		break;
+	case CPU_ONLINE:
+		/* Strictly unneccessary, as first user will wake it. */
+		wake_up_process(per_cpu(posix_timer_task,cpu));
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+		/* Unbind it from offline cpu so it can run.  Fall thru. */
+		kthread_bind(per_cpu(posix_timer_task, cpu),
+			     cpumask_any(cpu_online_mask));
+		kthread_stop(per_cpu(posix_timer_task,cpu));
+		per_cpu(posix_timer_task,cpu) = NULL;
+		break;
+	case CPU_DEAD:
+		kthread_stop(per_cpu(posix_timer_task,cpu));
+		per_cpu(posix_timer_task,cpu) = NULL;
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block posix_cpu_thread_notifier = {
+	.notifier_call = posix_cpu_thread_call,
+	.priority = 10
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+	void *hcpu = (void *)(long)smp_processor_id();
+	/* Start one for boot CPU. */
+	unsigned long cpu;
+
+	/* init the per-cpu posix_timer_tasklets */
+	for_each_possible_cpu(cpu)
+		per_cpu(posix_timer_tasklist, cpu) = NULL;
+
+	posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu);
+	posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu);
+	register_cpu_notifier(&posix_cpu_thread_notifier);
+	return 0;
+}
+early_initcall(posix_cpu_thread_init);
+#else /* CONFIG_PREEMPT_RT_BASE */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	__run_posix_cpu_timers(tsk);
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
 /*
  * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.