blob: 16af5cfa660e382ec8f461d24b8bfe4d0ce04f9b [file] [log] [blame]
From 9fd9af20640d4da2a4bd7311ffee1b5c7bd7b88f Mon Sep 17 00:00:00 2001
From: John Stultz <johnstul@us.ibm.com>
Date: Fri, 3 Jul 2009 08:29:58 -0500
Subject: [PATCH] posix-timers: thread posix-cpu-timers on -rt
commit 14cbf680c340564ac33e3518bf6c110d08d93cc9 in tip.
posix-cpu-timer code takes non -rt safe locks in hard irq
context. Move it to a thread.
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e93b8cd..cae32ed 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -167,6 +167,7 @@ extern struct cred init_cred;
.fs_excl = ATOMIC_INIT(0), \
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
.timer_slack_ns = 50000, /* 50 usec default slack */ \
+ .posix_timer_list = NULL, \
.pids = { \
[PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7e50287..7b23ee4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1370,6 +1370,8 @@ struct task_struct {
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
+ struct task_struct* posix_timer_list;
+
/* process credentials */
const struct cred *real_cred; /* objective and real subjective task
* credentials (COW) */
diff --git a/init/main.c b/init/main.c
index edabbff..650c1ce 100644
--- a/init/main.c
+++ b/init/main.c
@@ -36,6 +36,7 @@
#include <linux/workqueue.h>
#include <linux/profile.h>
#include <linux/rcupdate.h>
+#include <linux/posix-timers.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
#include <linux/writeback.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index bab0a66..334ebe7 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1090,7 +1090,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
acct_clear_integrals(p);
posix_cpu_timers_init(p);
-
+ p->posix_timer_list = NULL;
p->lock_depth = -1; /* -1 = no lock */
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 359cc24..36994bc 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -570,7 +570,7 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
p->cpu_timers : p->signal->cpu_timers);
head += CPUCLOCK_WHICH(timer->it_clock);
- BUG_ON(!irqs_disabled());
+ BUG_ON_NONRT(!irqs_disabled());
spin_lock(&p->sighand->siglock);
listpos = head;
@@ -749,7 +749,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
/*
* Disarm any old timer after extracting its expiry time.
*/
- BUG_ON(!irqs_disabled());
+ BUG_ON_NONRT(!irqs_disabled());
ret = 0;
spin_lock(&p->sighand->siglock);
@@ -1390,12 +1390,11 @@ 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)
+void __run_posix_cpu_timers(struct task_struct *tsk)
{
LIST_HEAD(firing);
struct k_itimer *timer, *next;
- BUG_ON(!irqs_disabled());
/*
* The fast path checks that there are no expired thread or thread
@@ -1447,6 +1446,162 @@ void run_posix_cpu_timers(struct task_struct *tsk)
}
}
+#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),
+ any_online_cpu(cpu_online_map));
+ 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 __devinitdata posix_cpu_thread_notifier = {
+ .notifier_call = posix_cpu_thread_call,
+ .priority = 10
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+ void *cpu = (void *)(long)smp_processor_id();
+ /* Start one for boot CPU. */
+ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, cpu);
+ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, cpu);
+ register_cpu_notifier(&posix_cpu_thread_notifier);
+ return 0;
+}
+early_initcall(posix_cpu_thread_init);
+
/*
* Set one of the process-wide special case CPU timers.
* The tsk->sighand->siglock must be held by the caller.
@@ -1713,6 +1868,12 @@ static __init int init_posix_cpu_timers(void)
.nsleep_restart = thread_cpu_nsleep_restart,
};
struct timespec ts;
+ unsigned long cpu;
+
+ /* init the per-cpu posix_timer_tasklets */
+ for_each_cpu_mask(cpu, cpu_possible_map) {
+ per_cpu(posix_timer_tasklist, cpu) = NULL;
+ }
register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
--
1.7.1.1