1 files changed, 717 insertions, 886 deletions

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 2eae91f954c..3b8946416a5 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -4,8 +4,29 @@
 
 #include <linux/sched.h>
 #include <linux/posix-timers.h>
-#include <asm/uaccess.h>
 #include <linux/errno.h>
+#include <linux/math64.h>
+#include <asm/uaccess.h>
+#include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
+#include <linux/random.h>
+#include <linux/tick.h>
+#include <linux/workqueue.h>
+
+/*
+ * Called after updating RLIMIT_CPU to run cpu timer and update
+ * tsk->signal->cputime_expires expiration cache if necessary. Needs
+ * siglock protection since other code may update expiration cache as
+ * well.
+ */
+void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
+{
+	cputime_t cputime = secs_to_cputime(rlim_new);
+
+	spin_lock_irq(&task->sighand->siglock);
+	set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+	spin_unlock_irq(&task->sighand->siglock);
+}
 
 static int check_clock(const clockid_t which_clock)
 {
@@ -19,85 +40,39 @@ static int check_clock(const clockid_t which_clock)
 	if (pid == 0)
 		return 0;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	p = find_task_by_vpid(pid);
 	if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
-		   same_thread_group(p, current) : thread_group_leader(p))) {
+		   same_thread_group(p, current) : has_group_leader_pid(p))) {
 		error = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return error;
 }
 
-static inline union cpu_time_count
+static inline unsigned long long
 timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
 {
-	union cpu_time_count ret;
-	ret.sched = 0;		/* high half always zero when .cpu used */
+	unsigned long long ret;
+
+	ret = 0;		/* high half always zero when .cpu used */
 	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
+		ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
 	} else {
-		ret.cpu = timespec_to_cputime(tp);
+		ret = cputime_to_expires(timespec_to_cputime(tp));
 	}
 	return ret;
 }
 
 static void sample_to_timespec(const clockid_t which_clock,
-			       union cpu_time_count cpu,
+			       unsigned long long expires,
 			       struct timespec *tp)
 {
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		tp->tv_sec = div_long_long_rem(cpu.sched,
-					       NSEC_PER_SEC, &tp->tv_nsec);
-	} else {
-		cputime_to_timespec(cpu.cpu, tp);
-	}
-}
-
-static inline int cpu_time_before(const clockid_t which_clock,
-				  union cpu_time_count now,
-				  union cpu_time_count then)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		return now.sched < then.sched;
-	}  else {
-		return cputime_lt(now.cpu, then.cpu);
-	}
-}
-static inline void cpu_time_add(const clockid_t which_clock,
-				union cpu_time_count *acc,
-			        union cpu_time_count val)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		acc->sched += val.sched;
-	}  else {
-		acc->cpu = cputime_add(acc->cpu, val.cpu);
-	}
-}
-static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
-						union cpu_time_count a,
-						union cpu_time_count b)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		a.sched -= b.sched;
-	}  else {
-		a.cpu = cputime_sub(a.cpu, b.cpu);
-	}
-	return a;
-}
-
-/*
- * Divide and limit the result to res >= 1
- *
- * This is necessary to prevent signal delivery starvation, when the result of
- * the division would be rounded down to 0.
- */
-static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
-{
-	cputime_t res = cputime_div(time, div);
-
-	return max_t(cputime_t, res, 1);
+	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
+		*tp = ns_to_timespec(expires);
+	else
+		cputime_to_timespec((__force cputime_t)expires, tp);
 }
 
 /*
@@ -105,66 +80,68 @@ static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
  * given the current clock sample.
  */
 static void bump_cpu_timer(struct k_itimer *timer,
-				  union cpu_time_count now)
+			   unsigned long long now)
 {
 	int i;
+	unsigned long long delta, incr;
 
-	if (timer->it.cpu.incr.sched == 0)
+	if (timer->it.cpu.incr == 0)
 		return;
 
-	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
-		unsigned long long delta, incr;
+	if (now < timer->it.cpu.expires)
+		return;
 
-		if (now.sched < timer->it.cpu.expires.sched)
-			return;
-		incr = timer->it.cpu.incr.sched;
-		delta = now.sched + incr - timer->it.cpu.expires.sched;
-		/* Don't use (incr*2 < delta), incr*2 might overflow. */
-		for (i = 0; incr < delta - incr; i++)
-			incr = incr << 1;
-		for (; i >= 0; incr >>= 1, i--) {
-			if (delta < incr)
-				continue;
-			timer->it.cpu.expires.sched += incr;
-			timer->it_overrun += 1 << i;
-			delta -= incr;
-		}
-	} else {
-		cputime_t delta, incr;
+	incr = timer->it.cpu.incr;
+	delta = now + incr - timer->it.cpu.expires;
 
-		if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
-			return;
-		incr = timer->it.cpu.incr.cpu;
-		delta = cputime_sub(cputime_add(now.cpu, incr),
-				    timer->it.cpu.expires.cpu);
-		/* Don't use (incr*2 < delta), incr*2 might overflow. */
-		for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
-			     incr = cputime_add(incr, incr);
-		for (; i >= 0; incr = cputime_halve(incr), i--) {
-			if (cputime_lt(delta, incr))
-				continue;
-			timer->it.cpu.expires.cpu =
-				cputime_add(timer->it.cpu.expires.cpu, incr);
-			timer->it_overrun += 1 << i;
-			delta = cputime_sub(delta, incr);
-		}
+	/* Don't use (incr*2 < delta), incr*2 might overflow. */
+	for (i = 0; incr < delta - incr; i++)
+		incr = incr << 1;
+
+	for (; i >= 0; incr >>= 1, i--) {
+		if (delta < incr)
+			continue;
+
+		timer->it.cpu.expires += incr;
+		timer->it_overrun += 1 << i;
+		delta -= incr;
 	}
 }
 
-static inline cputime_t prof_ticks(struct task_struct *p)
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime:	The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero.  Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
 {
-	return cputime_add(p->utime, p->stime);
+	if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime)
+		return 1;
+	return 0;
 }
-static inline cputime_t virt_ticks(struct task_struct *p)
+
+static inline unsigned long long prof_ticks(struct task_struct *p)
 {
-	return p->utime;
+	cputime_t utime, stime;
+
+	task_cputime(p, &utime, &stime);
+
+	return cputime_to_expires(utime + stime);
 }
-static inline unsigned long long sched_ns(struct task_struct *p)
+static inline unsigned long long virt_ticks(struct task_struct *p)
 {
-	return task_sched_runtime(p);
+	cputime_t utime;
+
+	task_cputime(p, &utime, NULL);
+
+	return cputime_to_expires(utime);
 }
 
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
 	int error = check_clock(which_clock);
 	if (!error) {
@@ -182,7 +159,8 @@ int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 	return error;
 }
 
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
 {
 	/*
 	 * You can never reset a CPU clock, but we check for other errors
@@ -200,104 +178,136 @@ int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
  * Sample a per-thread clock for the given task.
  */
 static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
-			    union cpu_time_count *cpu)
+			    unsigned long long *sample)
 {
 	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = prof_ticks(p);
+		*sample = prof_ticks(p);
 		break;
 	case CPUCLOCK_VIRT:
-		cpu->cpu = virt_ticks(p);
+		*sample = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = sched_ns(p);
+		*sample = task_sched_runtime(p);
 		break;
 	}
 	return 0;
 }
 
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+	if (b->utime > a->utime)
+		a->utime = b->utime;
+
+	if (b->stime > a->stime)
+		a->stime = b->stime;
+
+	if (b->sum_exec_runtime > a->sum_exec_runtime)
+		a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct task_cputime sum;
+	unsigned long flags;
+
+	if (!cputimer->running) {
+		/*
+		 * The POSIX timer interface allows for absolute time expiry
+		 * values through the TIMER_ABSTIME flag, therefore we have
+		 * to synchronize the timer to the clock every time we start
+		 * it.
+		 */
+		thread_group_cputime(tsk, &sum);
+		raw_spin_lock_irqsave(&cputimer->lock, flags);
+		cputimer->running = 1;
+		update_gt_cputime(&cputimer->cputime, &sum);
+	} else
+		raw_spin_lock_irqsave(&cputimer->lock, flags);
+	*times = cputimer->cputime;
+	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
-static int cpu_clock_sample_group_locked(unsigned int clock_idx,
-					 struct task_struct *p,
-					 union cpu_time_count *cpu)
+static int cpu_clock_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  unsigned long long *sample)
 {
-	struct task_struct *t = p;
- 	switch (clock_idx) {
+	struct task_cputime cputime;
+
+	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = cputime_add(p->signal->utime, p->signal->stime);
-		do {
-			cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t));
-			t = next_thread(t);
-		} while (t != p);
+		thread_group_cputime(p, &cputime);
+		*sample = cputime_to_expires(cputime.utime + cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
-		cpu->cpu = p->signal->utime;
-		do {
-			cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t));
-			t = next_thread(t);
-		} while (t != p);
+		thread_group_cputime(p, &cputime);
+		*sample = cputime_to_expires(cputime.utime);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = p->signal->sum_sched_runtime;
-		/* Add in each other live thread.  */
-		while ((t = next_thread(t)) != p) {
-			cpu->sched += t->se.sum_exec_runtime;
-		}
-		cpu->sched += sched_ns(p);
+		thread_group_cputime(p, &cputime);
+		*sample = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
 }
 
-/*
- * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_clock_sample_group(const clockid_t which_clock,
-				  struct task_struct *p,
-				  union cpu_time_count *cpu)
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+				    const clockid_t which_clock,
+				    struct timespec *tp)
 {
-	int ret;
-	unsigned long flags;
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
-					    cpu);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	return ret;
+	int err = -EINVAL;
+	unsigned long long rtn;
+
+	if (CPUCLOCK_PERTHREAD(which_clock)) {
+		if (same_thread_group(tsk, current))
+			err = cpu_clock_sample(which_clock, tsk, &rtn);
+	} else {
+		unsigned long flags;
+		struct sighand_struct *sighand;
+
+		/*
+		 * while_each_thread() is not yet entirely RCU safe,
+		 * keep locking the group while sampling process
+		 * clock for now.
+		 */
+		sighand = lock_task_sighand(tsk, &flags);
+		if (!sighand)
+			return err;
+
+		if (tsk == current || thread_group_leader(tsk))
+			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+		unlock_task_sighand(tsk, &flags);
+	}
+
+	if (!err)
+		sample_to_timespec(which_clock, rtn, tp);
+
+	return err;
 }
 
 
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
-	int error = -EINVAL;
-	union cpu_time_count rtn;
+	int err = -EINVAL;
 
 	if (pid == 0) {
 		/*
 		 * Special case constant value for our own clocks.
 		 * We don't have to do any lookup to find ourselves.
 		 */
-		if (CPUCLOCK_PERTHREAD(which_clock)) {
-			/*
-			 * Sampling just ourselves we can do with no locking.
-			 */
-			error = cpu_clock_sample(which_clock,
-						 current, &rtn);
-		} else {
-			read_lock(&tasklist_lock);
-			error = cpu_clock_sample_group(which_clock,
-						       current, &rtn);
-			read_unlock(&tasklist_lock);
-		}
+		err = posix_cpu_clock_get_task(current, which_clock, tp);
 	} else {
 		/*
 		 * Find the given PID, and validate that the caller
@@ -306,37 +316,21 @@ int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 		struct task_struct *p;
 		rcu_read_lock();
 		p = find_task_by_vpid(pid);
-		if (p) {
-			if (CPUCLOCK_PERTHREAD(which_clock)) {
-				if (same_thread_group(p, current)) {
-					error = cpu_clock_sample(which_clock,
-								 p, &rtn);
-				}
-			} else {
-				read_lock(&tasklist_lock);
-				if (thread_group_leader(p) && p->signal) {
-					error =
-					    cpu_clock_sample_group(which_clock,
-							           p, &rtn);
-				}
-				read_unlock(&tasklist_lock);
-			}
-		}
+		if (p)
+			err = posix_cpu_clock_get_task(p, which_clock, tp);
 		rcu_read_unlock();
 	}
 
-	if (error)
-		return error;
-	sample_to_timespec(which_clock, rtn, tp);
-	return 0;
+	return err;
 }
 
 
 /*
  * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
- * This is called from sys_timer_create with the new timer already locked.
+ * This is called from sys_timer_create() and do_cpu_nanosleep() with the
+ * new timer already all-zeros initialized.
  */
-int posix_cpu_timer_create(struct k_itimer *new_timer)
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
 {
 	int ret = 0;
 	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
@@ -346,10 +340,8 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
-	new_timer->it.cpu.incr.sched = 0;
-	new_timer->it.cpu.expires.sched = 0;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
 		if (pid == 0) {
 			p = current;
@@ -363,7 +355,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 			p = current->group_leader;
 		} else {
 			p = find_task_by_vpid(pid);
-			if (p && !thread_group_leader(p))
+			if (p && !has_group_leader_pid(p))
 				p = NULL;
 		}
 	}
@@ -373,7 +365,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 	} else {
 		ret = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -384,79 +376,60 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_del(struct k_itimer *timer)
+static int posix_cpu_timer_del(struct k_itimer *timer)
 {
-	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
+	unsigned long flags;
+	struct sighand_struct *sighand;
+	struct task_struct *p = timer->it.cpu.task;
 
-	if (likely(p != NULL)) {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->signal == NULL)) {
-			/*
-			 * We raced with the reaping of the task.
-			 * The deletion should have cleared us off the list.
-			 */
-			BUG_ON(!list_empty(&timer->it.cpu.entry));
-		} else {
-			spin_lock(&p->sighand->siglock);
-			if (timer->it.cpu.firing)
-				ret = TIMER_RETRY;
-			else
-				list_del(&timer->it.cpu.entry);
-			spin_unlock(&p->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
+	WARN_ON_ONCE(p == NULL);
+
+	/*
+	 * Protect against sighand release/switch in exit/exec and process/
+	 * thread timer list entry concurrent read/writes.
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	if (unlikely(sighand == NULL)) {
+		/*
+		 * We raced with the reaping of the task.
+		 * The deletion should have cleared us off the list.
+		 */
+		WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+	} else {
+		if (timer->it.cpu.firing)
+			ret = TIMER_RETRY;
+		else
+			list_del(&timer->it.cpu.entry);
 
-		if (!ret)
-			put_task_struct(p);
+		unlock_task_sighand(p, &flags);
 	}
 
+	if (!ret)
+		put_task_struct(p);
+
 	return ret;
 }
 
+static void cleanup_timers_list(struct list_head *head)
+{
+	struct cpu_timer_list *timer, *next;
+
+	list_for_each_entry_safe(timer, next, head, entry)
+		list_del_init(&timer->entry);
+}
+
 /*
  * Clean out CPU timers still ticking when a thread exited.  The task
  * pointer is cleared, and the expiry time is replaced with the residual
  * time for later timer_gettime calls to return.
  * This must be called with the siglock held.
  */
-static void cleanup_timers(struct list_head *head,
-			   cputime_t utime, cputime_t stime,
-			   unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
 {
-	struct cpu_timer_list *timer, *next;
-	cputime_t ptime = cputime_add(utime, stime);
-
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (cputime_lt(timer->expires.cpu, ptime)) {
-			timer->expires.cpu = cputime_zero;
-		} else {
-			timer->expires.cpu = cputime_sub(timer->expires.cpu,
-							 ptime);
-		}
-	}
-
-	++head;
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (cputime_lt(timer->expires.cpu, utime)) {
-			timer->expires.cpu = cputime_zero;
-		} else {
-			timer->expires.cpu = cputime_sub(timer->expires.cpu,
-							 utime);
-		}
-	}
-
-	++head;
-	list_for_each_entry_safe(timer, next, head, entry) {
-		list_del_init(&timer->entry);
-		if (timer->expires.sched < sum_exec_runtime) {
-			timer->expires.sched = 0;
-		} else {
-			timer->expires.sched -= sum_exec_runtime;
-		}
-	}
+	cleanup_timers_list(head);
+	cleanup_timers_list(++head);
+	cleanup_timers_list(++head);
 }
 
 /*
@@ -466,206 +439,76 @@ static void cleanup_timers(struct list_head *head,
  */
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
-	cleanup_timers(tsk->cpu_timers,
-		       tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
+	add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
+						sizeof(unsigned long long));
+	cleanup_timers(tsk->cpu_timers);
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	cleanup_timers(tsk->signal->cpu_timers,
-		       cputime_add(tsk->utime, tsk->signal->utime),
-		       cputime_add(tsk->stime, tsk->signal->stime),
-		     tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime);
-}
-
-
-/*
- * Set the expiry times of all the threads in the process so one of them
- * will go off before the process cumulative expiry total is reached.
- */
-static void process_timer_rebalance(struct task_struct *p,
-				    unsigned int clock_idx,
-				    union cpu_time_count expires,
-				    union cpu_time_count val)
-{
-	cputime_t ticks, left;
-	unsigned long long ns, nsleft;
- 	struct task_struct *t = p;
-	unsigned int nthreads = atomic_read(&p->signal->live);
-
-	if (!nthreads)
-		return;
-
-	switch (clock_idx) {
-	default:
-		BUG();
-		break;
-	case CPUCLOCK_PROF:
-		left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-				       nthreads);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ticks = cputime_add(prof_ticks(t), left);
-				if (cputime_eq(t->it_prof_expires,
-					       cputime_zero) ||
-				    cputime_gt(t->it_prof_expires, ticks)) {
-					t->it_prof_expires = ticks;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	case CPUCLOCK_VIRT:
-		left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-				       nthreads);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ticks = cputime_add(virt_ticks(t), left);
-				if (cputime_eq(t->it_virt_expires,
-					       cputime_zero) ||
-				    cputime_gt(t->it_virt_expires, ticks)) {
-					t->it_virt_expires = ticks;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	case CPUCLOCK_SCHED:
-		nsleft = expires.sched - val.sched;
-		do_div(nsleft, nthreads);
-		nsleft = max_t(unsigned long long, nsleft, 1);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ns = t->se.sum_exec_runtime + nsleft;
-				if (t->it_sched_expires == 0 ||
-				    t->it_sched_expires > ns) {
-					t->it_sched_expires = ns;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	}
+	cleanup_timers(tsk->signal->cpu_timers);
 }
 
-static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 {
-	/*
-	 * That's all for this thread or process.
-	 * We leave our residual in expires to be reported.
-	 */
-	put_task_struct(timer->it.cpu.task);
-	timer->it.cpu.task = NULL;
-	timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
-					     timer->it.cpu.expires,
-					     now);
+	return expires == 0 || expires > new_exp;
 }
 
 /*
  * Insert the timer on the appropriate list before any timers that
- * expire later.  This must be called with the tasklist_lock held
- * for reading, and interrupts disabled.
+ * expire later.  This must be called with the sighand lock held.
  */
-static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
+static void arm_timer(struct k_itimer *timer)
 {
 	struct task_struct *p = timer->it.cpu.task;
 	struct list_head *head, *listpos;
+	struct task_cputime *cputime_expires;
 	struct cpu_timer_list *const nt = &timer->it.cpu;
 	struct cpu_timer_list *next;
-	unsigned long i;
 
-	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
-		p->cpu_timers : p->signal->cpu_timers);
+	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+		head = p->cpu_timers;
+		cputime_expires = &p->cputime_expires;
+	} else {
+		head = p->signal->cpu_timers;
+		cputime_expires = &p->signal->cputime_expires;
+	}
 	head += CPUCLOCK_WHICH(timer->it_clock);
 
-	BUG_ON(!irqs_disabled());
-	spin_lock(&p->sighand->siglock);
-
 	listpos = head;
-	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
-		list_for_each_entry(next, head, entry) {
-			if (next->expires.sched > nt->expires.sched)
-				break;
-			listpos = &next->entry;
-		}
-	} else {
-		list_for_each_entry(next, head, entry) {
-			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
-				break;
-			listpos = &next->entry;
-		}
+	list_for_each_entry(next, head, entry) {
+		if (nt->expires < next->expires)
+			break;
+		listpos = &next->entry;
 	}
 	list_add(&nt->entry, listpos);
 
 	if (listpos == head) {
+		unsigned long long exp = nt->expires;
+
 		/*
-		 * We are the new earliest-expiring timer.
-		 * If we are a thread timer, there can always
-		 * be a process timer telling us to stop earlier.
+		 * We are the new earliest-expiring POSIX 1.b timer, hence
+		 * need to update expiration cache. Take into account that
+		 * for process timers we share expiration cache with itimers
+		 * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
 		 */
 
-		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_PROF:
-				if (cputime_eq(p->it_prof_expires,
-					       cputime_zero) ||
-				    cputime_gt(p->it_prof_expires,
-					       nt->expires.cpu))
-					p->it_prof_expires = nt->expires.cpu;
-				break;
-			case CPUCLOCK_VIRT:
-				if (cputime_eq(p->it_virt_expires,
-					       cputime_zero) ||
-				    cputime_gt(p->it_virt_expires,
-					       nt->expires.cpu))
-					p->it_virt_expires = nt->expires.cpu;
-				break;
-			case CPUCLOCK_SCHED:
-				if (p->it_sched_expires == 0 ||
-				    p->it_sched_expires > nt->expires.sched)
-					p->it_sched_expires = nt->expires.sched;
-				break;
-			}
-		} else {
-			/*
-			 * For a process timer, we must balance
-			 * all the live threads' expirations.
-			 */
-			switch (CPUCLOCK_WHICH(timer->it_clock)) {
-			default:
-				BUG();
-			case CPUCLOCK_VIRT:
-				if (!cputime_eq(p->signal->it_virt_expires,
-						cputime_zero) &&
-				    cputime_lt(p->signal->it_virt_expires,
-					       timer->it.cpu.expires.cpu))
-					break;
-				goto rebalance;
-			case CPUCLOCK_PROF:
-				if (!cputime_eq(p->signal->it_prof_expires,
-						cputime_zero) &&
-				    cputime_lt(p->signal->it_prof_expires,
-					       timer->it.cpu.expires.cpu))
-					break;
-				i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
-				if (i != RLIM_INFINITY &&
-				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
-					break;
-				goto rebalance;
-			case CPUCLOCK_SCHED:
-			rebalance:
-				process_timer_rebalance(
-					timer->it.cpu.task,
-					CPUCLOCK_WHICH(timer->it_clock),
-					timer->it.cpu.expires, now);
-				break;
-			}
+		switch (CPUCLOCK_WHICH(timer->it_clock)) {
+		case CPUCLOCK_PROF:
+			if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
+				cputime_expires->prof_exp = expires_to_cputime(exp);
+			break;
+		case CPUCLOCK_VIRT:
+			if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
+				cputime_expires->virt_exp = expires_to_cputime(exp);
+			break;
+		case CPUCLOCK_SCHED:
+			if (cputime_expires->sched_exp == 0 ||
+			    cputime_expires->sched_exp > exp)
+				cputime_expires->sched_exp = exp;
+			break;
 		}
 	}
-
-	spin_unlock(&p->sighand->siglock);
 }
 
 /*
@@ -673,19 +516,24 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
  */
 static void cpu_timer_fire(struct k_itimer *timer)
 {
-	if (unlikely(timer->sigq == NULL)) {
+	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
+		/*
+		 * User don't want any signal.
+		 */
+		timer->it.cpu.expires = 0;
+	} else if (unlikely(timer->sigq == NULL)) {
 		/*
 		 * This a special case for clock_nanosleep,
 		 * not a normal timer from sys_timer_create.
 		 */
 		wake_up_process(timer->it_process);
-		timer->it.cpu.expires.sched = 0;
-	} else if (timer->it.cpu.incr.sched == 0) {
+		timer->it.cpu.expires = 0;
+	} else if (timer->it.cpu.incr == 0) {
 		/*
 		 * One-shot timer.  Clear it as soon as it's fired.
 		 */
 		posix_timer_event(timer, 0);
-		timer->it.cpu.expires.sched = 0;
+		timer->it.cpu.expires = 0;
 	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
 		/*
 		 * The signal did not get queued because the signal
@@ -698,54 +546,110 @@ static void cpu_timer_fire(struct k_itimer *timer)
 }
 
 /*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  unsigned long long *sample)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputimer(p, &cputime);
+	switch (CPUCLOCK_WHICH(which_clock)) {
+	default:
+		return -EINVAL;
+	case CPUCLOCK_PROF:
+		*sample = cputime_to_expires(cputime.utime + cputime.stime);
+		break;
+	case CPUCLOCK_VIRT:
+		*sample = cputime_to_expires(cputime.utime);
+		break;
+	case CPUCLOCK_SCHED:
+		*sample = cputime.sum_exec_runtime + task_delta_exec(p);
+		break;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+static void nohz_kick_work_fn(struct work_struct *work)
+{
+	tick_nohz_full_kick_all();
+}
+
+static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
+
+/*
+ * We need the IPIs to be sent from sane process context.
+ * The posix cpu timers are always set with irqs disabled.
+ */
+static void posix_cpu_timer_kick_nohz(void)
+{
+	if (context_tracking_is_enabled())
+		schedule_work(&nohz_kick_work);
+}
+
+bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
+{
+	if (!task_cputime_zero(&tsk->cputime_expires))
+		return false;
+
+	if (tsk->signal->cputimer.running)
+		return false;
+
+	return true;
+}
+#else
+static inline void posix_cpu_timer_kick_nohz(void) { }
+#endif
+
+/*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-			struct itimerspec *new, struct itimerspec *old)
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
+			       struct itimerspec *new, struct itimerspec *old)
 {
+	unsigned long flags;
+	struct sighand_struct *sighand;
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count old_expires, new_expires, val;
+	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * Timer refers to a dead task's clock.
-		 */
-		return -ESRCH;
-	}
+	WARN_ON_ONCE(p == NULL);
 
 	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
 
-	read_lock(&tasklist_lock);
 	/*
-	 * We need the tasklist_lock to protect against reaping that
-	 * clears p->signal.  If p has just been reaped, we can no
+	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
+	 * and p->signal->cpu_timers read/write in arm_timer()
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	/*
+	 * If p has just been reaped, we can no
 	 * longer get any information about it at all.
 	 */
-	if (unlikely(p->signal == NULL)) {
-		read_unlock(&tasklist_lock);
-		put_task_struct(p);
-		timer->it.cpu.task = NULL;
+	if (unlikely(sighand == NULL)) {
 		return -ESRCH;
 	}
 
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	ret = 0;
-	spin_lock(&p->sighand->siglock);
+	old_incr = timer->it.cpu.incr;
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
 		timer->it.cpu.firing = -1;
 		ret = TIMER_RETRY;
 	} else
 		list_del_init(&timer->it.cpu.entry);
-	spin_unlock(&p->sighand->siglock);
 
 	/*
 	 * We need to sample the current value to convert the new
@@ -758,11 +662,11 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &val);
 	} else {
-		cpu_clock_sample_group(timer->it_clock, p, &val);
+		cpu_timer_sample_group(timer->it_clock, p, &val);
 	}
 
 	if (old) {
-		if (old_expires.sched == 0) {
+		if (old_expires == 0) {
 			old->it_value.tv_sec = 0;
 			old->it_value.tv_nsec = 0;
 		} else {
@@ -777,11 +681,8 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 			 * new setting.
 			 */
 			bump_cpu_timer(timer, val);
-			if (cpu_time_before(timer->it_clock, val,
-					    timer->it.cpu.expires)) {
-				old_expires = cpu_time_sub(
-					timer->it_clock,
-					timer->it.cpu.expires, val);
+			if (val < timer->it.cpu.expires) {
+				old_expires = timer->it.cpu.expires - val;
 				sample_to_timespec(timer->it_clock,
 						   old_expires,
 						   &old->it_value);
@@ -799,12 +700,12 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
-		read_unlock(&tasklist_lock);
+		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
-		cpu_time_add(timer->it_clock, &new_expires, val);
+	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
+		new_expires += val;
 	}
 
 	/*
@@ -813,14 +714,11 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	 * arm the timer (we'll just fake it for timer_gettime).
 	 */
 	timer->it.cpu.expires = new_expires;
-	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
-	    cpu_time_before(timer->it_clock, val, new_expires)) {
-		arm_timer(timer, val);
+	if (new_expires != 0 && val < new_expires) {
+		arm_timer(timer);
 	}
 
-	read_unlock(&tasklist_lock);
-
+	unlock_task_sighand(p, &flags);
 	/*
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
@@ -838,9 +736,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	timer->it_overrun_last = 0;
 	timer->it_overrun = -1;
 
-	if (new_expires.sched != 0 &&
-	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
-	    !cpu_time_before(timer->it_clock, val, new_expires)) {
+	if (new_expires != 0 && !(val < new_expires)) {
 		/*
 		 * The designated time already passed, so we notify
 		 * immediately, even if the thread never runs to
@@ -853,16 +749,19 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
  out:
 	if (old) {
 		sample_to_timespec(timer->it_clock,
-				   timer->it.cpu.incr, &old->it_interval);
+				   old_incr, &old->it_interval);
 	}
+	if (!ret)
+		posix_cpu_timer_kick_nohz();
 	return ret;
 }
 
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
-	union cpu_time_count now;
+	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
-	int clear_dead;
+
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Easy part: convert the reload time.
@@ -870,82 +769,44 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	sample_to_timespec(timer->it_clock,
 			   timer->it.cpu.incr, &itp->it_interval);
 
-	if (timer->it.cpu.expires.sched == 0) {	/* Timer not armed at all.  */
+	if (timer->it.cpu.expires == 0) {	/* Timer not armed at all.  */
 		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
 		return;
 	}
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * This task already died and the timer will never fire.
-		 * In this case, expires is actually the dead value.
-		 */
-	dead:
-		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
-				   &itp->it_value);
-		return;
-	}
-
 	/*
 	 * Sample the clock to take the difference with the expiry time.
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
-		clear_dead = p->exit_state;
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->signal == NULL)) {
+		struct sighand_struct *sighand;
+		unsigned long flags;
+
+		/*
+		 * Protect against sighand release/switch in exit/exec and
+		 * also make timer sampling safe if it ends up calling
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 * Call the timer disarmed, nothing else to do.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = NULL;
-			timer->it.cpu.expires.sched = 0;
-			read_unlock(&tasklist_lock);
-			goto dead;
+			timer->it.cpu.expires = 0;
+			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+					   &itp->it_value);
 		} else {
-			cpu_clock_sample_group(timer->it_clock, p, &now);
-			clear_dead = (unlikely(p->exit_state) &&
-				      thread_group_empty(p));
+			cpu_timer_sample_group(timer->it_clock, p, &now);
+			unlock_task_sighand(p, &flags);
 		}
-		read_unlock(&tasklist_lock);
-	}
-
-	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
-		if (timer->it.cpu.incr.sched == 0 &&
-		    cpu_time_before(timer->it_clock,
-				    timer->it.cpu.expires, now)) {
-			/*
-			 * Do-nothing timer expired and has no reload,
-			 * so it's as if it was never set.
-			 */
-			timer->it.cpu.expires.sched = 0;
-			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
-			return;
-		}
-		/*
-		 * Account for any expirations and reloads that should
-		 * have happened.
-		 */
-		bump_cpu_timer(timer, now);
-	}
-
-	if (unlikely(clear_dead)) {
-		/*
-		 * We've noticed that the thread is dead, but
-		 * not yet reaped.  Take this opportunity to
-		 * drop our task ref.
-		 */
-		clear_dead_task(timer, now);
-		goto dead;
 	}
 
-	if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
+	if (now < timer->it.cpu.expires) {
 		sample_to_timespec(timer->it_clock,
-				   cpu_time_sub(timer->it_clock,
-						timer->it.cpu.expires, now),
+				   timer->it.cpu.expires - now,
 				   &itp->it_value);
 	} else {
 		/*
@@ -957,6 +818,28 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	}
 }
 
+static unsigned long long
+check_timers_list(struct list_head *timers,
+		  struct list_head *firing,
+		  unsigned long long curr)
+{
+	int maxfire = 20;
+
+	while (!list_empty(timers)) {
+		struct cpu_timer_list *t;
+
+		t = list_first_entry(timers, struct cpu_timer_list, entry);
+
+		if (!--maxfire || curr < t->expires)
+			return t->expires;
+
+		t->firing = 1;
+		list_move_tail(&t->entry, firing);
+	}
+
+	return 0;
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them off
  * the tsk->cpu_timers[N] list onto the firing list.  Here we update the
@@ -965,60 +848,28 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 static void check_thread_timers(struct task_struct *tsk,
 				struct list_head *firing)
 {
-	int maxfire;
 	struct list_head *timers = tsk->cpu_timers;
 	struct signal_struct *const sig = tsk->signal;
+	struct task_cputime *tsk_expires = &tsk->cputime_expires;
+	unsigned long long expires;
+	unsigned long soft;
 
-	maxfire = 20;
-	tsk->it_prof_expires = cputime_zero;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
-			tsk->it_prof_expires = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	expires = check_timers_list(timers, firing, prof_ticks(tsk));
+	tsk_expires->prof_exp = expires_to_cputime(expires);
 
-	++timers;
-	maxfire = 20;
-	tsk->it_virt_expires = cputime_zero;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
-			tsk->it_virt_expires = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	expires = check_timers_list(++timers, firing, virt_ticks(tsk));
+	tsk_expires->virt_exp = expires_to_cputime(expires);
 
-	++timers;
-	maxfire = 20;
-	tsk->it_sched_expires = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
-			tsk->it_sched_expires = t->expires.sched;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	tsk_expires->sched_exp = check_timers_list(++timers, firing,
+						   tsk->se.sum_exec_runtime);
 
 	/*
 	 * Check for the special case thread timers.
 	 */
-	if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
-		unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
-		unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
+	soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+	if (soft != RLIM_INFINITY) {
+		unsigned long hard =
+			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
 
 		if (hard != RLIM_INFINITY &&
 		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
@@ -1029,20 +880,64 @@ static void check_thread_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
-		if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) {
+		if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
-			if (sig->rlim[RLIMIT_RTTIME].rlim_cur
-			    < sig->rlim[RLIMIT_RTTIME].rlim_max) {
-				sig->rlim[RLIMIT_RTTIME].rlim_cur +=
-								USEC_PER_SEC;
+			if (soft < hard) {
+				soft += USEC_PER_SEC;
+				sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
 			}
+			printk(KERN_INFO
+				"RT Watchdog Timeout: %s[%d]\n",
+				tsk->comm, task_pid_nr(tsk));
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 		}
 	}
 }
 
+static void stop_process_timers(struct signal_struct *sig)
+{
+	struct thread_group_cputimer *cputimer = &sig->cputimer;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&cputimer->lock, flags);
+	cputimer->running = 0;
+	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+			     unsigned long long *expires,
+			     unsigned long long cur_time, int signo)
+{
+	if (!it->expires)
+		return;
+
+	if (cur_time >= it->expires) {
+		if (it->incr) {
+			it->expires += it->incr;
+			it->error += it->incr_error;
+			if (it->error >= onecputick) {
+				it->expires -= cputime_one_jiffy;
+				it->error -= onecputick;
+			}
+		} else {
+			it->expires = 0;
+		}
+
+		trace_itimer_expire(signo == SIGPROF ?
+				    ITIMER_PROF : ITIMER_VIRTUAL,
+				    tsk->signal->leader_pid, cur_time);
+		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+	}
+
+	if (it->expires && (!*expires || it->expires < *expires)) {
+		*expires = it->expires;
+	}
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -1051,122 +946,39 @@ static void check_thread_timers(struct task_struct *tsk,
 static void check_process_timers(struct task_struct *tsk,
 				 struct list_head *firing)
 {
-	int maxfire;
 	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, stime, ptime, virt_expires, prof_expires;
+	unsigned long long utime, ptime, virt_expires, prof_expires;
 	unsigned long long sum_sched_runtime, sched_expires;
-	struct task_struct *t;
 	struct list_head *timers = sig->cpu_timers;
-
-	/*
-	 * Don't sample the current process CPU clocks if there are no timers.
-	 */
-	if (list_empty(&timers[CPUCLOCK_PROF]) &&
-	    cputime_eq(sig->it_prof_expires, cputime_zero) &&
-	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
-	    list_empty(&timers[CPUCLOCK_VIRT]) &&
-	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
-	    list_empty(&timers[CPUCLOCK_SCHED]))
-		return;
+	struct task_cputime cputime;
+	unsigned long soft;
 
 	/*
 	 * Collect the current process totals.
 	 */
-	utime = sig->utime;
-	stime = sig->stime;
-	sum_sched_runtime = sig->sum_sched_runtime;
-	t = tsk;
-	do {
-		utime = cputime_add(utime, t->utime);
-		stime = cputime_add(stime, t->stime);
-		sum_sched_runtime += t->se.sum_exec_runtime;
-		t = next_thread(t);
-	} while (t != tsk);
-	ptime = cputime_add(utime, stime);
-
-	maxfire = 20;
-	prof_expires = cputime_zero;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || cputime_lt(ptime, t->expires.cpu)) {
-			prof_expires = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	thread_group_cputimer(tsk, &cputime);
+	utime = cputime_to_expires(cputime.utime);
+	ptime = utime + cputime_to_expires(cputime.stime);
+	sum_sched_runtime = cputime.sum_exec_runtime;
 
-	++timers;
-	maxfire = 20;
-	virt_expires = cputime_zero;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || cputime_lt(utime, t->expires.cpu)) {
-			virt_expires = t->expires.cpu;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
-
-	++timers;
-	maxfire = 20;
-	sched_expires = 0;
-	while (!list_empty(timers)) {
-		struct cpu_timer_list *t = list_first_entry(timers,
-						      struct cpu_timer_list,
-						      entry);
-		if (!--maxfire || sum_sched_runtime < t->expires.sched) {
-			sched_expires = t->expires.sched;
-			break;
-		}
-		t->firing = 1;
-		list_move_tail(&t->entry, firing);
-	}
+	prof_expires = check_timers_list(timers, firing, ptime);
+	virt_expires = check_timers_list(++timers, firing, utime);
+	sched_expires = check_timers_list(++timers, firing, sum_sched_runtime);
 
 	/*
 	 * Check for the special case process timers.
 	 */
-	if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-		if (cputime_ge(ptime, sig->it_prof_expires)) {
-			/* ITIMER_PROF fires and reloads.  */
-			sig->it_prof_expires = sig->it_prof_incr;
-			if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-				sig->it_prof_expires = cputime_add(
-					sig->it_prof_expires, ptime);
-			}
-			__group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
-		}
-		if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
-		    (cputime_eq(prof_expires, cputime_zero) ||
-		     cputime_lt(sig->it_prof_expires, prof_expires))) {
-			prof_expires = sig->it_prof_expires;
-		}
-	}
-	if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-		if (cputime_ge(utime, sig->it_virt_expires)) {
-			/* ITIMER_VIRTUAL fires and reloads.  */
-			sig->it_virt_expires = sig->it_virt_incr;
-			if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-				sig->it_virt_expires = cputime_add(
-					sig->it_virt_expires, utime);
-			}
-			__group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
-		}
-		if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
-		    (cputime_eq(virt_expires, cputime_zero) ||
-		     cputime_lt(sig->it_virt_expires, virt_expires))) {
-			virt_expires = sig->it_virt_expires;
-		}
-	}
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+			 SIGPROF);
+	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+			 SIGVTALRM);
+	soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	if (soft != RLIM_INFINITY) {
 		unsigned long psecs = cputime_to_secs(ptime);
+		unsigned long hard =
+			ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
 		cputime_t x;
-		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
+		if (psecs >= hard) {
 			/*
 			 * At the hard limit, we just die.
 			 * No need to calculate anything else now.
@@ -1174,77 +986,27 @@ static void check_process_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
-		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
+		if (psecs >= soft) {
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
-			if (sig->rlim[RLIMIT_CPU].rlim_cur
-			    < sig->rlim[RLIMIT_CPU].rlim_max) {
-				sig->rlim[RLIMIT_CPU].rlim_cur++;
+			if (soft < hard) {
+				soft++;
+				sig->rlim[RLIMIT_CPU].rlim_cur = soft;
 			}
 		}
-		x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-		if (cputime_eq(prof_expires, cputime_zero) ||
-		    cputime_lt(x, prof_expires)) {
+		x = secs_to_cputime(soft);
+		if (!prof_expires || x < prof_expires) {
 			prof_expires = x;
 		}
 	}
 
-	if (!cputime_eq(prof_expires, cputime_zero) ||
-	    !cputime_eq(virt_expires, cputime_zero) ||
-	    sched_expires != 0) {
-		/*
-		 * Rebalance the threads' expiry times for the remaining
-		 * process CPU timers.
-		 */
-
-		cputime_t prof_left, virt_left, ticks;
-		unsigned long long sched_left, sched;
-		const unsigned int nthreads = atomic_read(&sig->live);
-
-		if (!nthreads)
-			return;
-
-		prof_left = cputime_sub(prof_expires, utime);
-		prof_left = cputime_sub(prof_left, stime);
-		prof_left = cputime_div_non_zero(prof_left, nthreads);
-		virt_left = cputime_sub(virt_expires, utime);
-		virt_left = cputime_div_non_zero(virt_left, nthreads);
-		if (sched_expires) {
-			sched_left = sched_expires - sum_sched_runtime;
-			do_div(sched_left, nthreads);
-			sched_left = max_t(unsigned long long, sched_left, 1);
-		} else {
-			sched_left = 0;
-		}
-		t = tsk;
-		do {
-			if (unlikely(t->flags & PF_EXITING))
-				continue;
-
-			ticks = cputime_add(cputime_add(t->utime, t->stime),
-					    prof_left);
-			if (!cputime_eq(prof_expires, cputime_zero) &&
-			    (cputime_eq(t->it_prof_expires, cputime_zero) ||
-			     cputime_gt(t->it_prof_expires, ticks))) {
-				t->it_prof_expires = ticks;
-			}
-
-			ticks = cputime_add(t->utime, virt_left);
-			if (!cputime_eq(virt_expires, cputime_zero) &&
-			    (cputime_eq(t->it_virt_expires, cputime_zero) ||
-			     cputime_gt(t->it_virt_expires, ticks))) {
-				t->it_virt_expires = ticks;
-			}
-
-			sched = t->se.sum_exec_runtime + sched_left;
-			if (sched_expires && (t->it_sched_expires == 0 ||
-					      t->it_sched_expires > sched)) {
-				t->it_sched_expires = sched;
-			}
-		} while ((t = next_thread(t)) != tsk);
-	}
+	sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
+	sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
+	sig->cputime_expires.sched_exp = sched_expires;
+	if (task_cputime_zero(&sig->cputime_expires))
+		stop_process_timers(sig);
 }
 
 /*
@@ -1253,14 +1015,12 @@ static void check_process_timers(struct task_struct *tsk,
  */
 void posix_cpu_timer_schedule(struct k_itimer *timer)
 {
+	struct sighand_struct *sighand;
+	unsigned long flags;
 	struct task_struct *p = timer->it.cpu.task;
-	union cpu_time_count now;
+	unsigned long long now;
 
-	if (unlikely(p == NULL))
-		/*
-		 * The task was cleaned up already, no future firings.
-		 */
-		goto out;
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1268,50 +1028,117 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		if (unlikely(p->exit_state)) {
-			clear_dead_task(timer, now);
+		if (unlikely(p->exit_state))
+			goto out;
+
+		/* Protect timer list r/w in arm_timer() */
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
 			goto out;
-		}
-		read_lock(&tasklist_lock); /* arm_timer needs it.  */
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->signal == NULL)) {
+		/*
+		 * Protect arm_timer() and timer sampling in case of call to
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = p = NULL;
-			timer->it.cpu.expires.sched = 0;
-			goto out_unlock;
+			timer->it.cpu.expires = 0;
+			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			/*
-			 * We've noticed that the thread is dead, but
-			 * not yet reaped.  Take this opportunity to
-			 * drop our task ref.
-			 */
-			clear_dead_task(timer, now);
-			goto out_unlock;
+			unlock_task_sighand(p, &flags);
+			/* Optimizations: if the process is dying, no need to rearm */
+			goto out;
 		}
-		cpu_clock_sample_group(timer->it_clock, p, &now);
+		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		/* Leave the tasklist_lock locked for the call below.  */
+		/* Leave the sighand locked for the call below.  */
 	}
 
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	arm_timer(timer, now);
-
-out_unlock:
-	read_unlock(&tasklist_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+	arm_timer(timer);
+	unlock_task_sighand(p, &flags);
 
+	/* Kick full dynticks CPUs in case they need to tick on the new timer */
+	posix_cpu_timer_kick_nohz();
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
 	++timer->it_requeue_pending;
 }
 
+/**
+ * task_cputime_expired - Compare two task_cputime entities.
+ *
+ * @sample:	The task_cputime structure to be checked for expiration.
+ * @expires:	Expiration times, against which @sample will be checked.
+ *
+ * Checks @sample against @expires to see if any field of @sample has expired.
+ * Returns true if any field of the former is greater than the corresponding
+ * field of the latter if the latter field is set.  Otherwise returns false.
+ */
+static inline int task_cputime_expired(const struct task_cputime *sample,
+					const struct task_cputime *expires)
+{
+	if (expires->utime && sample->utime >= expires->utime)
+		return 1;
+	if (expires->stime && sample->utime + sample->stime >= expires->stime)
+		return 1;
+	if (expires->sum_exec_runtime != 0 &&
+	    sample->sum_exec_runtime >= expires->sum_exec_runtime)
+		return 1;
+	return 0;
+}
+
+/**
+ * fastpath_timer_check - POSIX CPU timers fast path.
+ *
+ * @tsk:	The task (thread) being checked.
+ *
+ * Check the task and thread group timers.  If both are zero (there are no
+ * timers set) return false.  Otherwise snapshot the task and thread group
+ * timers and compare them with the corresponding expiration times.  Return
+ * true if a timer has expired, else return false.
+ */
+static inline int fastpath_timer_check(struct task_struct *tsk)
+{
+	struct signal_struct *sig;
+	cputime_t utime, stime;
+
+	task_cputime(tsk, &utime, &stime);
+
+	if (!task_cputime_zero(&tsk->cputime_expires)) {
+		struct task_cputime task_sample = {
+			.utime = utime,
+			.stime = stime,
+			.sum_exec_runtime = tsk->se.sum_exec_runtime
+		};
+
+		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+			return 1;
+	}
+
+	sig = tsk->signal;
+	if (sig->cputimer.running) {
+		struct task_cputime group_sample;
+
+		raw_spin_lock(&sig->cputimer.lock);
+		group_sample = sig->cputimer.cputime;
+		raw_spin_unlock(&sig->cputimer.lock);
+
+		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * This is called from the timer interrupt handler.  The irq handler has
  * already updated our counts.  We need to check if any timers fire now.
@@ -1321,126 +1148,114 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
+	unsigned long flags;
 
-	BUG_ON(!irqs_disabled());
-
-#define UNEXPIRED(clock) \
-		(cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \
-		 cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires))
+	WARN_ON_ONCE(!irqs_disabled());
 
-	if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
-	    (tsk->it_sched_expires == 0 ||
-	     tsk->se.sum_exec_runtime < tsk->it_sched_expires))
+	/*
+	 * The fast path checks that there are no expired thread or thread
+	 * group timers.  If that's so, just return.
+	 */
+	if (!fastpath_timer_check(tsk))
 		return;
 
-#undef	UNEXPIRED
-
+	if (!lock_task_sighand(tsk, &flags))
+		return;
 	/*
-	 * Double-check with locks held.
+	 * Here we take off tsk->signal->cpu_timers[N] and
+	 * tsk->cpu_timers[N] all the timers that are firing, and
+	 * put them on the firing list.
 	 */
-	read_lock(&tasklist_lock);
-	if (likely(tsk->signal != NULL)) {
-		spin_lock(&tsk->sighand->siglock);
-
-		/*
-		 * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
-		 * all the timers that are firing, and put them on the firing list.
-		 */
-		check_thread_timers(tsk, &firing);
+	check_thread_timers(tsk, &firing);
+	/*
+	 * If there are any active process wide timers (POSIX 1.b, itimers,
+	 * RLIMIT_CPU) cputimer must be running.
+	 */
+	if (tsk->signal->cputimer.running)
 		check_process_timers(tsk, &firing);
 
-		/*
-		 * We must release these locks before taking any timer's lock.
-		 * There is a potential race with timer deletion here, as the
-		 * siglock now protects our private firing list.  We have set
-		 * the firing flag in each timer, so that a deletion attempt
-		 * that gets the timer lock before we do will give it up and
-		 * spin until we've taken care of that timer below.
-		 */
-		spin_unlock(&tsk->sighand->siglock);
-	}
-	read_unlock(&tasklist_lock);
+	/*
+	 * We must release these locks before taking any timer's lock.
+	 * There is a potential race with timer deletion here, as the
+	 * siglock now protects our private firing list.  We have set
+	 * the firing flag in each timer, so that a deletion attempt
+	 * that gets the timer lock before we do will give it up and
+	 * spin until we've taken care of that timer below.
+	 */
+	unlock_task_sighand(tsk, &flags);
 
 	/*
 	 * Now that all the timers on our list have the firing flag,
-	 * noone will touch their list entries but us.  We'll take
+	 * no one will touch their list entries but us.  We'll take
 	 * each timer's lock before clearing its firing flag, so no
 	 * timer call will interfere.
 	 */
 	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
-		int firing;
+		int cpu_firing;
+
 		spin_lock(&timer->it_lock);
 		list_del_init(&timer->it.cpu.entry);
-		firing = timer->it.cpu.firing;
+		cpu_firing = timer->it.cpu.firing;
 		timer->it.cpu.firing = 0;
 		/*
 		 * The firing flag is -1 if we collided with a reset
 		 * of the timer, which already reported this
 		 * almost-firing as an overrun.  So don't generate an event.
 		 */
-		if (likely(firing >= 0)) {
+		if (likely(cpu_firing >= 0))
 			cpu_timer_fire(timer);
-		}
 		spin_unlock(&timer->it_lock);
 	}
 }
 
 /*
- * Set one of the process-wide special case CPU timers.
- * The tasklist_lock and tsk->sighand->siglock must be held by the caller.
- * The oldval argument is null for the RLIMIT_CPU timer, where *newval is
- * absolute; non-null for ITIMER_*, where *newval is relative and we update
- * it to be absolute, *oldval is absolute and we update it to be relative.
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
+ * The tsk->sighand->siglock must be held by the caller.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval)
 {
-	union cpu_time_count now;
-	struct list_head *head;
+	unsigned long long now;
 
-	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	cpu_clock_sample_group_locked(clock_idx, tsk, &now);
+	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
+	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
-		if (!cputime_eq(*oldval, cputime_zero)) {
-			if (cputime_le(*oldval, now.cpu)) {
+		/*
+		 * We are setting itimer. The *oldval is absolute and we update
+		 * it to be relative, *newval argument is relative and we update
+		 * it to be absolute.
+		 */
+		if (*oldval) {
+			if (*oldval <= now) {
 				/* Just about to fire. */
-				*oldval = jiffies_to_cputime(1);
+				*oldval = cputime_one_jiffy;
 			} else {
-				*oldval = cputime_sub(*oldval, now.cpu);
+				*oldval -= now;
 			}
 		}
 
-		if (cputime_eq(*newval, cputime_zero))
-			return;
-		*newval = cputime_add(*newval, now.cpu);
-
-		/*
-		 * If the RLIMIT_CPU timer will expire before the
-		 * ITIMER_PROF timer, we have nothing else to do.
-		 */
-		if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
-		    < cputime_to_secs(*newval))
-			return;
+		if (!*newval)
+			goto out;
+		*newval += now;
 	}
 
 	/*
-	 * Check whether there are any process timers already set to fire
-	 * before this one.  If so, we don't have anything more to do.
+	 * Update expiration cache if we are the earliest timer, or eventually
+	 * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
 	 */
-	head = &tsk->signal->cpu_timers[clock_idx];
-	if (list_empty(head) ||
-	    cputime_ge(list_first_entry(head,
-				  struct cpu_timer_list, entry)->expires.cpu,
-		       *newval)) {
-		/*
-		 * Rejigger each thread's expiry time so that one will
-		 * notice before we hit the process-cumulative expiry time.
-		 */
-		union cpu_time_count expires = { .sched = 0 };
-		expires.cpu = *newval;
-		process_timer_rebalance(tsk, clock_idx, expires, now);
+	switch (clock_idx) {
+	case CPUCLOCK_PROF:
+		if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
+			tsk->signal->cputime_expires.prof_exp = *newval;
+		break;
+	case CPUCLOCK_VIRT:
+		if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
+			tsk->signal->cputime_expires.virt_exp = *newval;
+		break;
 	}
+out:
+	posix_cpu_timer_kick_nohz();
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
@@ -1472,10 +1287,12 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		}
 
 		while (!signal_pending(current)) {
-			if (timer.it.cpu.expires.sched == 0) {
+			if (timer.it.cpu.expires == 0) {
 				/*
-				 * Our timer fired and was reset.
+				 * Our timer fired and was reset, below
+				 * deletion can not fail.
 				 */
+				posix_cpu_timer_del(&timer);
 				spin_unlock_irq(&timer.it_lock);
 				return 0;
 			}
@@ -1493,9 +1310,26 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		 * We were interrupted by a signal.
 		 */
 		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
-		posix_cpu_timer_set(&timer, 0, &zero_it, it);
+		error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
+		if (!error) {
+			/*
+			 * Timer is now unarmed, deletion can not fail.
+			 */
+			posix_cpu_timer_del(&timer);
+		}
 		spin_unlock_irq(&timer.it_lock);
 
+		while (error == TIMER_RETRY) {
+			/*
+			 * We need to handle case when timer was or is in the
+			 * middle of firing. In other cases we already freed
+			 * resources.
+			 */
+			spin_lock_irq(&timer.it_lock);
+			error = posix_cpu_timer_del(&timer);
+			spin_unlock_irq(&timer.it_lock);
+		}
+
 		if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
 			/*
 			 * It actually did fire already.
@@ -1509,11 +1343,13 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	return error;
 }
 
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-		     struct timespec *rqtp, struct timespec __user *rmtp)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
 	struct restart_block *restart_block =
-	    &current_thread_info()->restart_block;
+		&current_thread_info()->restart_block;
 	struct itimerspec it;
 	int error;
 
@@ -1529,56 +1365,47 @@ int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 
 	if (error == -ERESTART_RESTARTBLOCK) {
 
-	       	if (flags & TIMER_ABSTIME)
+		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
 		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = rqtp->tv_sec;
-		restart_block->arg3 = rqtp->tv_nsec;
+		restart_block->nanosleep.clockid = which_clock;
+		restart_block->nanosleep.rmtp = rmtp;
+		restart_block->nanosleep.expires = timespec_to_ns(rqtp);
 	}
 	return error;
 }
 
-long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
 {
-	clockid_t which_clock = restart_block->arg0;
-	struct timespec __user *rmtp;
+	clockid_t which_clock = restart_block->nanosleep.clockid;
 	struct timespec t;
 	struct itimerspec it;
 	int error;
 
-	rmtp = (struct timespec __user *) restart_block->arg1;
-	t.tv_sec = restart_block->arg2;
-	t.tv_nsec = restart_block->arg3;
+	t = ns_to_timespec(restart_block->nanosleep.expires);
 
-	restart_block->fn = do_no_restart_syscall;
 	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
 
 	if (error == -ERESTART_RESTARTBLOCK) {
+		struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
 		/*
-	 	 * Report back to the user the time still remaining.
-	 	 */
-		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+		 * Report back to the user the time still remaining.
+		 */
+		if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
 			return -EFAULT;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
-		restart_block->arg0 = which_clock;
-		restart_block->arg1 = (unsigned long) rmtp;
-		restart_block->arg2 = t.tv_sec;
-		restart_block->arg3 = t.tv_nsec;
+		restart_block->nanosleep.expires = timespec_to_ns(&t);
 	}
 	return error;
 
 }
 
-
 #define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
 #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
 
@@ -1622,37 +1449,41 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
 	timer->it_clock = THREAD_CLOCK;
 	return posix_cpu_timer_create(timer);
 }
-static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
-			      struct timespec *rqtp, struct timespec __user *rmtp)
-{
-	return -EINVAL;
-}
-static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
-{
-	return -EINVAL;
-}
+
+struct k_clock clock_posix_cpu = {
+	.clock_getres	= posix_cpu_clock_getres,
+	.clock_set	= posix_cpu_clock_set,
+	.clock_get	= posix_cpu_clock_get,
+	.timer_create	= posix_cpu_timer_create,
+	.nsleep		= posix_cpu_nsleep,
+	.nsleep_restart	= posix_cpu_nsleep_restart,
+	.timer_set	= posix_cpu_timer_set,
+	.timer_del	= posix_cpu_timer_del,
+	.timer_get	= posix_cpu_timer_get,
+};
 
 static __init int init_posix_cpu_timers(void)
 {
 	struct k_clock process = {
-		.clock_getres = process_cpu_clock_getres,
-		.clock_get = process_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = process_cpu_timer_create,
-		.nsleep = process_cpu_nsleep,
-		.nsleep_restart = process_cpu_nsleep_restart,
+		.clock_getres	= process_cpu_clock_getres,
+		.clock_get	= process_cpu_clock_get,
+		.timer_create	= process_cpu_timer_create,
+		.nsleep		= process_cpu_nsleep,
+		.nsleep_restart	= process_cpu_nsleep_restart,
 	};
 	struct k_clock thread = {
-		.clock_getres = thread_cpu_clock_getres,
-		.clock_get = thread_cpu_clock_get,
-		.clock_set = do_posix_clock_nosettime,
-		.timer_create = thread_cpu_timer_create,
-		.nsleep = thread_cpu_nsleep,
-		.nsleep_restart = thread_cpu_nsleep_restart,
+		.clock_getres	= thread_cpu_clock_getres,
+		.clock_get	= thread_cpu_clock_get,
+		.timer_create	= thread_cpu_timer_create,
 	};
+	struct timespec ts;
+
+	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
-	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
-	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+	cputime_to_timespec(cputime_one_jiffy, &ts);
+	onecputick = ts.tv_nsec;
+	WARN_ON(ts.tv_sec != 0);
 
 	return 0;
 }