Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core timer updates from Thomas Gleixner:
 "Timers and timekeeping updates:

   - A large overhaul of the posix CPU timer code which is a preparation
     for moving the CPU timer expiry out into task work so it can be
     properly accounted on the task/process.

     An update to the bogus permission checks will come later during the
     merge window as feedback was not complete before heading of for
     travel.

   - Switch the timerqueue code to use cached rbtrees and get rid of the
     homebrewn caching of the leftmost node.

   - Consolidate hrtimer_init() + hrtimer_init_sleeper() calls into a
     single function

   - Implement the separation of hrtimers to be forced to expire in hard
     interrupt context even when PREEMPT_RT is enabled and mark the
     affected timers accordingly.

   - Implement a mechanism for hrtimers and the timer wheel to protect
     RT against priority inversion and live lock issues when a (hr)timer
     which should be canceled is currently executing the callback.
     Instead of infinitely spinning, the task which tries to cancel the
     timer blocks on a per cpu base expiry lock which is held and
     released by the (hr)timer expiry code.

   - Enable the Hyper-V TSC page based sched_clock for Hyper-V guests
     resulting in faster access to timekeeping functions.

   - Updates to various clocksource/clockevent drivers and their device
     tree bindings.

   - The usual small improvements all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (101 commits)
  posix-cpu-timers: Fix permission check regression
  posix-cpu-timers: Always clear head pointer on dequeue
  hrtimer: Add a missing bracket and hide `migration_base' on !SMP
  posix-cpu-timers: Make expiry_active check actually work correctly
  posix-timers: Unbreak CONFIG_POSIX_TIMERS=n build
  tick: Mark sched_timer to expire in hard interrupt context
  hrtimer: Add kernel doc annotation for HRTIMER_MODE_HARD
  x86/hyperv: Hide pv_ops access for CONFIG_PARAVIRT=n
  posix-cpu-timers: Utilize timerqueue for storage
  posix-cpu-timers: Move state tracking to struct posix_cputimers
  posix-cpu-timers: Deduplicate rlimit handling
  posix-cpu-timers: Remove pointless comparisons
  posix-cpu-timers: Get rid of 64bit divisions
  posix-cpu-timers: Consolidate timer expiry further
  posix-cpu-timers: Get rid of zero checks
  rlimit: Rewrite non-sensical RLIMIT_CPU comment
  posix-cpu-timers: Respect INFINITY for hard RTTIME limit
  posix-cpu-timers: Switch thread group sampling to array
  posix-cpu-timers: Restructure expiry array
  posix-cpu-timers: Remove cputime_expires
  ...

3 files changed, 15 insertions, 12 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 06961b997ed6..5e8387bdd09c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -255,7 +255,7 @@ static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
 
-	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
 }
 
 /*
@@ -314,7 +314,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 */
 	delay = max_t(u64, delay, 10000LL);
 	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
-		      HRTIMER_MODE_REL_PINNED);
+		      HRTIMER_MODE_REL_PINNED_HARD);
 }
 #endif /* CONFIG_SMP */
 
@@ -328,7 +328,7 @@ static void hrtick_rq_init(struct rq *rq)
 	rq->hrtick_csd.info = rq;
 #endif
 
-	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	rq->hrtick_timer.function = hrtick;
 }
 #else	/* CONFIG_SCHED_HRTICK */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 39dc9f74f289..2dc48720f189 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p)
 
 	dl_se->dl_non_contending = 1;
 	get_task_struct(p);
-	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
 }
 
 static void task_contending(struct sched_dl_entity *dl_se, int flags)
@@ -956,7 +956,7 @@ static int start_dl_timer(struct task_struct *p)
 	 */
 	if (!hrtimer_is_queued(timer)) {
 		get_task_struct(p);
-		hrtimer_start(timer, act, HRTIMER_MODE_ABS);
+		hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
 	}
 
 	return 1;
@@ -1086,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = dl_task_timer;
 }
 
@@ -1325,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = inactive_task_timer;
 }
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 858c4cc6f99b..ebaa4e619684 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 
 	raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
-	hrtimer_init(&rt_b->rt_period_timer,
-			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_HARD);
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
@@ -67,7 +67,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 		 * to update the period.
 		 */
 		hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
-		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+		hrtimer_start_expires(&rt_b->rt_period_timer,
+				      HRTIMER_MODE_ABS_PINNED_HARD);
 	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -2289,8 +2290,10 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 		}
 
 		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
-		if (p->rt.timeout > next)
-			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
+		if (p->rt.timeout > next) {
+			posix_cputimers_rt_watchdog(&p->posix_cputimers,
+						    p->se.sum_exec_runtime);
+		}
 	}
 }
 #else