[PATCH] hrtimer: switch itimers to hrtimer

switch itimers to a hrtimers-based implementation

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/exec.c

@@ -632,10 +632,10 @@ static inline int de_thread(struct task_struct *tsk)
 		 * synchronize with any firing (by calling del_timer_sync)
 		 * before we can safely let the old group leader die.
 		 */
-		sig->real_timer.data = (unsigned long)current;
+		sig->real_timer.data = current;
 		spin_unlock_irq(lock);
-		if (del_timer_sync(&sig->real_timer))
+		if (hrtimer_cancel(&sig->real_timer))
-			add_timer(&sig->real_timer);
+			hrtimer_restart(&sig->real_timer);
 		spin_lock_irq(lock);
 	}
 	while (atomic_read(&sig->count) > count) {

fs/proc/array.c

@@ -330,7 +330,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
 	unsigned long  min_flt = 0,  maj_flt = 0;
 	cputime_t cutime, cstime, utime, stime;
 	unsigned long rsslim = 0;
-	unsigned long it_real_value = 0;
+	DEFINE_KTIME(it_real_value);
 	struct task_struct *t;
 	char tcomm[sizeof(task->comm)];
 
@@ -386,7 +386,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
 			utime = cputime_add(utime, task->signal->utime);
 			stime = cputime_add(stime, task->signal->stime);
 		}
-		it_real_value = task->signal->it_real_value;
+		it_real_value = task->signal->real_timer.expires;
 	}
 	ppid = pid_alive(task) ? task->group_leader->real_parent->tgid : 0;
 	read_unlock(&tasklist_lock);
@@ -435,7 +435,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
 		priority,
 		nice,
 		num_threads,
-		jiffies_to_clock_t(it_real_value),
+		(long) ktime_to_clock_t(it_real_value),
 		start_time,
 		vsize,
 		mm ? get_mm_rss(mm) : 0,

include/linux/sched.h

@@ -105,6 +105,7 @@ extern unsigned long nr_iowait(void);
 #include <linux/param.h>
 #include <linux/resource.h>
 #include <linux/timer.h>
+#include <linux/hrtimer.h>
 
 #include <asm/processor.h>
 
@@ -398,8 +399,8 @@ struct signal_struct {
 	struct list_head posix_timers;
 
 	/* ITIMER_REAL timer for the process */
-	struct timer_list real_timer;
+	struct hrtimer real_timer;
-	unsigned long it_real_value, it_real_incr;
+	ktime_t it_real_incr;
 
 	/* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
 	cputime_t it_prof_expires, it_virt_expires;

include/linux/timer.h

@@ -96,6 +96,6 @@ static inline void add_timer(struct timer_list *timer)
 
 extern void init_timers(void);
 extern void run_local_timers(void);
-extern void it_real_fn(unsigned long);
+extern int it_real_fn(void *);
 
 #endif

kernel/exit.c

@@ -842,7 +842,7 @@ fastcall NORET_TYPE void do_exit(long code)
 	}
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
- 		del_timer_sync(&tsk->signal->real_timer);
+ 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
 		acct_process(code);
 	}

kernel/fork.c

@@ -801,10 +801,10 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
 
-	sig->it_real_value = sig->it_real_incr = 0;
+	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC);
+	sig->it_real_incr.tv64 = 0;
 	sig->real_timer.function = it_real_fn;
-	sig->real_timer.data = (unsigned long) tsk;
+	sig->real_timer.data = tsk;
-	init_timer(&sig->real_timer);
 
 	sig->it_virt_expires = cputime_zero;
 	sig->it_virt_incr = cputime_zero;

kernel/itimer.c

@@ -12,36 +12,46 @@
 #include <linux/syscalls.h>
 #include <linux/time.h>
 #include <linux/posix-timers.h>
+#include <linux/hrtimer.h>
 
 #include <asm/uaccess.h>
 
-static unsigned long it_real_value(struct signal_struct *sig)
+/**
+ * itimer_get_remtime - get remaining time for the timer
+ *
+ * @timer: the timer to read
+ *
+ * Returns the delta between the expiry time and now, which can be
+ * less than zero or 1usec for an pending expired timer
+ */
+static struct timeval itimer_get_remtime(struct hrtimer *timer)
 {
-	unsigned long val = 0;
+	ktime_t rem = hrtimer_get_remaining(timer);
-	if (timer_pending(&sig->real_timer)) {
-		val = sig->real_timer.expires - jiffies;
 
-		/* look out for negative/zero itimer.. */
+	/*
-		if ((long) val <= 0)
+	 * Racy but safe: if the itimer expires after the above
-			val = 1;
+	 * hrtimer_get_remtime() call but before this condition
-	}
+	 * then we return 0 - which is correct.
-	return val;
+	 */
+	if (hrtimer_active(timer)) {
+		if (rem.tv64 <= 0)
+			rem.tv64 = NSEC_PER_USEC;
+	} else
+		rem.tv64 = 0;
+
+	return ktime_to_timeval(rem);
 }
 
 int do_getitimer(int which, struct itimerval *value)
 {
 	struct task_struct *tsk = current;
-	unsigned long interval, val;
 	cputime_t cinterval, cval;
 
 	switch (which) {
 	case ITIMER_REAL:
-		spin_lock_irq(&tsk->sighand->siglock);
+		value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
-		interval = tsk->signal->it_real_incr;
+		value->it_interval =
-		val = it_real_value(tsk->signal);
+			ktime_to_timeval(tsk->signal->it_real_incr);
-		spin_unlock_irq(&tsk->sighand->siglock);
-		jiffies_to_timeval(val, &value->it_value);
-		jiffies_to_timeval(interval, &value->it_interval);
 		break;
 	case ITIMER_VIRTUAL:
 		read_lock(&tasklist_lock);
@@ -113,59 +123,45 @@ asmlinkage long sys_getitimer(int which, struct itimerval __user *value)
 }
 
 
-void it_real_fn(unsigned long __data)
+/*
+ * The timer is automagically restarted, when interval != 0
+ */
+int it_real_fn(void *data)
 {
-	struct task_struct * p = (struct task_struct *) __data;
+	struct task_struct *tsk = (struct task_struct *) data;
-	unsigned long inc = p->signal->it_real_incr;
 
-	send_group_sig_info(SIGALRM, SEND_SIG_PRIV, p);
+	send_group_sig_info(SIGALRM, SEND_SIG_PRIV, tsk);
 
-	/*
+	if (tsk->signal->it_real_incr.tv64 != 0) {
-	 * Now restart the timer if necessary.  We don't need any locking
+		hrtimer_forward(&tsk->signal->real_timer,
-	 * here because do_setitimer makes sure we have finished running
+			       tsk->signal->it_real_incr);
-	 * before it touches anything.
+
-	 * Note, we KNOW we are (or should be) at a jiffie edge here so
+		return HRTIMER_RESTART;
-	 * we don't need the +1 stuff.  Also, we want to use the prior
+	}
-	 * expire value so as to not "slip" a jiffie if we are late.
+	return HRTIMER_NORESTART;
-	 * Deal with requesting a time prior to "now" here rather than
-	 * in add_timer.
-	 */
-	if (!inc)
-		return;
-	while (time_before_eq(p->signal->real_timer.expires, jiffies))
-		p->signal->real_timer.expires += inc;
-	add_timer(&p->signal->real_timer);
 }
 
 int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 {
 	struct task_struct *tsk = current;
- 	unsigned long val, interval, expires;
+	struct hrtimer *timer;
+	ktime_t expires;
 	cputime_t cval, cinterval, nval, ninterval;
 
 	switch (which) {
 	case ITIMER_REAL:
-again:
+		timer = &tsk->signal->real_timer;
-		spin_lock_irq(&tsk->sighand->siglock);
+		hrtimer_cancel(timer);
-		interval = tsk->signal->it_real_incr;
+		if (ovalue) {
-		val = it_real_value(tsk->signal);
+			ovalue->it_value = itimer_get_remtime(timer);
-		/* We are sharing ->siglock with it_real_fn() */
+			ovalue->it_interval
-		if (try_to_del_timer_sync(&tsk->signal->real_timer) < 0) {
+				= ktime_to_timeval(tsk->signal->it_real_incr);
-			spin_unlock_irq(&tsk->sighand->siglock);
-			goto again;
 		}
 		tsk->signal->it_real_incr =
-			timeval_to_jiffies(&value->it_interval);
+			timeval_to_ktime(value->it_interval);
-		expires = timeval_to_jiffies(&value->it_value);
+		expires = timeval_to_ktime(value->it_value);
-		if (expires)
+		if (expires.tv64 != 0)
-			mod_timer(&tsk->signal->real_timer,
+			hrtimer_start(timer, expires, HRTIMER_REL);
-				  jiffies + 1 + expires);
-		spin_unlock_irq(&tsk->sighand->siglock);
-		if (ovalue) {
-			jiffies_to_timeval(val, &ovalue->it_value);
-			jiffies_to_timeval(interval,
-					   &ovalue->it_interval);
-		}
 		break;
 	case ITIMER_VIRTUAL:
 		nval = timeval_to_cputime(&value->it_value);