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
  ...

13 files changed, 223 insertions, 86 deletions

diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index 0becb7d9704d..18d8e2d8210f 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -167,6 +167,7 @@ void hyperv_report_panic(struct pt_regs *regs, long err);
 void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 bool hv_is_hyperv_initialized(void);
 void hyperv_cleanup(void);
+void hv_setup_sched_clock(void *sched_clock);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline void hyperv_cleanup(void) {}
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index a821deb8ecb2..422f5e5237be 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -28,12 +28,10 @@ extern void hv_stimer_cleanup(unsigned int cpu);
 extern void hv_stimer_global_cleanup(void);
 extern void hv_stimer0_isr(void);
 
-#if IS_ENABLED(CONFIG_HYPERV)
+#ifdef CONFIG_HYPERV_TIMER
 extern struct clocksource *hyperv_cs;
 extern void hv_init_clocksource(void);
-#endif /* CONFIG_HYPERV */
 
-#ifdef CONFIG_HYPERV_TSCPAGE
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 
 static inline notrace u64
@@ -91,7 +89,7 @@ hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
 }
 
-#else /* CONFIG_HYPERV_TSC_PAGE */
+#else /* CONFIG_HYPERV_TIMER */
 static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return NULL;
@@ -102,6 +100,6 @@ static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
 {
 	return U64_MAX;
 }
-#endif /* CONFIG_HYPERV_TSCPAGE */
+#endif /* CONFIG_HYPERV_TIMER */
 
 #endif
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 0760ca1cb009..74748e306f4b 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -5,7 +5,8 @@
 #include <linux/time.h>
 #include <linux/hrtimer.h>
 #include <linux/timerqueue.h>
-#include <linux/rtc.h>
+
+struct rtc_device;
 
 enum alarmtimer_type {
 	ALARM_REALTIME,
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 4971100a8cab..1b9a51a1bccb 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -32,12 +32,15 @@ struct hrtimer_cpu_base;
  *				  when starting the timer)
  * HRTIMER_MODE_SOFT		- Timer callback function will be executed in
  *				  soft irq context
+ * HRTIMER_MODE_HARD		- Timer callback function will be executed in
+ *				  hard irq context even on PREEMPT_RT.
  */
 enum hrtimer_mode {
 	HRTIMER_MODE_ABS	= 0x00,
 	HRTIMER_MODE_REL	= 0x01,
 	HRTIMER_MODE_PINNED	= 0x02,
 	HRTIMER_MODE_SOFT	= 0x04,
+	HRTIMER_MODE_HARD	= 0x08,
 
 	HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
 	HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
@@ -48,6 +51,11 @@ enum hrtimer_mode {
 	HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
 	HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
 
+	HRTIMER_MODE_ABS_HARD	= HRTIMER_MODE_ABS | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_HARD	= HRTIMER_MODE_REL | HRTIMER_MODE_HARD,
+
+	HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD,
+	HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
 };
 
 /*
@@ -101,6 +109,8 @@ enum hrtimer_restart {
  * @state:	state information (See bit values above)
  * @is_rel:	Set if the timer was armed relative
  * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
+ * @is_hard:	Set if hrtimer will be expired in hard interrupt context
+ *		even on RT.
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -112,6 +122,7 @@ struct hrtimer {
 	u8				state;
 	u8				is_rel;
 	u8				is_soft;
+	u8				is_hard;
 };
 
 /**
@@ -183,6 +194,10 @@ enum  hrtimer_base_type {
  * @nr_retries:		Total number of hrtimer interrupt retries
  * @nr_hangs:		Total number of hrtimer interrupt hangs
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
+ * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
+ *			 expired
+ * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
+ *			callback to finish.
  * @expires_next:	absolute time of the next event, is required for remote
  *			hrtimer enqueue; it is the total first expiry time (hard
  *			and soft hrtimer are taken into account)
@@ -210,6 +225,10 @@ struct hrtimer_cpu_base {
 	unsigned short			nr_hangs;
 	unsigned int			max_hang_time;
 #endif
+#ifdef CONFIG_PREEMPT_RT
+	spinlock_t			softirq_expiry_lock;
+	atomic_t			timer_waiters;
+#endif
 	ktime_t				expires_next;
 	struct hrtimer			*next_timer;
 	ktime_t				softirq_expires_next;
@@ -341,16 +360,29 @@ extern void hrtimers_resume(void);
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
 
+#ifdef CONFIG_PREEMPT_RT
+void hrtimer_cancel_wait_running(const struct hrtimer *timer);
+#else
+static inline void hrtimer_cancel_wait_running(struct hrtimer *timer)
+{
+	cpu_relax();
+}
+#endif
 
 /* Exported timer functions: */
 
 /* Initialize timers: */
 extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
 			 enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
+				 enum hrtimer_mode mode);
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
 				  enum hrtimer_mode mode);
+extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+					  clockid_t clock_id,
+					  enum hrtimer_mode mode);
 
 extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
 #else
@@ -360,6 +392,14 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer,
 {
 	hrtimer_init(timer, which_clock, mode);
 }
+
+static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
+						 clockid_t clock_id,
+						 enum hrtimer_mode mode)
+{
+	hrtimer_init_sleeper(sl, clock_id, mode);
+}
+
 static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
@@ -395,6 +435,9 @@ static inline void hrtimer_start_expires(struct hrtimer *timer,
 	hrtimer_start_range_ns(timer, soft, delta, mode);
 }
 
+void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
+				   enum hrtimer_mode mode);
+
 static inline void hrtimer_restart(struct hrtimer *timer)
 {
 	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
@@ -463,11 +506,8 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp,
 			      const enum hrtimer_mode mode,
 			      const clockid_t clockid);
 
-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
-				 struct task_struct *tsk);
-
 extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
-						const enum hrtimer_mode mode);
+				    const enum hrtimer_mode mode);
 extern int schedule_hrtimeout_range_clock(ktime_t *expires,
 					  u64 delta,
 					  const enum hrtimer_mode mode,
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6049baa5b8bc..2c620d7ac432 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -36,17 +36,6 @@ extern struct cred init_cred;
 #define INIT_PREV_CPUTIME(x)
 #endif
 
-#ifdef CONFIG_POSIX_TIMERS
-#define INIT_CPU_TIMERS(s)						\
-	.cpu_timers = {							\
-		LIST_HEAD_INIT(s.cpu_timers[0]),			\
-		LIST_HEAD_INIT(s.cpu_timers[1]),			\
-		LIST_HEAD_INIT(s.cpu_timers[2]),			\
-	},
-#else
-#define INIT_CPU_TIMERS(s)
-#endif
-
 #define INIT_TASK_COMM "swapper"
 
 /* Attach to the init_task data structure for proper alignment */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index b20798fc5191..3d10c84a97a9 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -4,18 +4,11 @@
 
 #include <linux/spinlock.h>
 #include <linux/list.h>
-#include <linux/sched.h>
-#include <linux/timex.h>
 #include <linux/alarmtimer.h>
+#include <linux/timerqueue.h>
 
-struct siginfo;
-
-struct cpu_timer_list {
-	struct list_head entry;
-	u64 expires;
-	struct task_struct *task;
-	int firing;
-};
+struct kernel_siginfo;
+struct task_struct;
 
 /*
  * Bit fields within a clockid:
@@ -63,6 +56,115 @@ static inline int clockid_to_fd(const clockid_t clk)
 	return ~(clk >> 3);
 }
 
+#ifdef CONFIG_POSIX_TIMERS
+
+/**
+ * cpu_timer - Posix CPU timer representation for k_itimer
+ * @node:	timerqueue node to queue in the task/sig
+ * @head:	timerqueue head on which this timer is queued
+ * @task:	Pointer to target task
+ * @elist:	List head for the expiry list
+ * @firing:	Timer is currently firing
+ */
+struct cpu_timer {
+	struct timerqueue_node	node;
+	struct timerqueue_head	*head;
+	struct task_struct	*task;
+	struct list_head	elist;
+	int			firing;
+};
+
+static inline bool cpu_timer_enqueue(struct timerqueue_head *head,
+				     struct cpu_timer *ctmr)
+{
+	ctmr->head = head;
+	return timerqueue_add(head, &ctmr->node);
+}
+
+static inline void cpu_timer_dequeue(struct cpu_timer *ctmr)
+{
+	if (ctmr->head) {
+		timerqueue_del(ctmr->head, &ctmr->node);
+		ctmr->head = NULL;
+	}
+}
+
+static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr)
+{
+	return ctmr->node.expires;
+}
+
+static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp)
+{
+	ctmr->node.expires = exp;
+}
+
+/**
+ * posix_cputimer_base - Container per posix CPU clock
+ * @nextevt:		Earliest-expiration cache
+ * @tqhead:		timerqueue head for cpu_timers
+ */
+struct posix_cputimer_base {
+	u64			nextevt;
+	struct timerqueue_head	tqhead;
+};
+
+/**
+ * posix_cputimers - Container for posix CPU timer related data
+ * @bases:		Base container for posix CPU clocks
+ * @timers_active:	Timers are queued.
+ * @expiry_active:	Timer expiry is active. Used for
+ *			process wide timers to avoid multiple
+ *			task trying to handle expiry concurrently
+ *
+ * Used in task_struct and signal_struct
+ */
+struct posix_cputimers {
+	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
+	unsigned int			timers_active;
+	unsigned int			expiry_active;
+};
+
+static inline void posix_cputimers_init(struct posix_cputimers *pct)
+{
+	memset(pct, 0, sizeof(*pct));
+	pct->bases[0].nextevt = U64_MAX;
+	pct->bases[1].nextevt = U64_MAX;
+	pct->bases[2].nextevt = U64_MAX;
+}
+
+void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit);
+
+static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct,
+					       u64 runtime)
+{
+	pct->bases[CPUCLOCK_SCHED].nextevt = runtime;
+}
+
+/* Init task static initializer */
+#define INIT_CPU_TIMERBASE(b) {						\
+	.nextevt	= U64_MAX,					\
+}
+
+#define INIT_CPU_TIMERBASES(b) {					\
+	INIT_CPU_TIMERBASE(b[0]),					\
+	INIT_CPU_TIMERBASE(b[1]),					\
+	INIT_CPU_TIMERBASE(b[2]),					\
+}
+
+#define INIT_CPU_TIMERS(s)						\
+	.posix_cputimers = {						\
+		.bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases),	\
+	},
+#else
+struct posix_cputimers { };
+struct cpu_timer { };
+#define INIT_CPU_TIMERS(s)
+static inline void posix_cputimers_init(struct posix_cputimers *pct) { }
+static inline void posix_cputimers_group_init(struct posix_cputimers *pct,
+					      u64 cpu_limit) { }
+#endif
+
 #define REQUEUE_PENDING 1
 
 /**
@@ -85,7 +187,8 @@ static inline int clockid_to_fd(const clockid_t clk)
  * @it_process:		The task to wakeup on clock_nanosleep (CPU timers)
  * @sigq:		Pointer to preallocated sigqueue
  * @it:			Union representing the various posix timer type
- *			internals. Also used for rcu freeing the timer.
+ *			internals.
+ * @rcu:		RCU head for freeing the timer.
  */
 struct k_itimer {
 	struct list_head	list;
@@ -110,15 +213,15 @@ struct k_itimer {
 		struct {
 			struct hrtimer	timer;
 		} real;
-		struct cpu_timer_list	cpu;
+		struct cpu_timer	cpu;
 		struct {
 			struct alarm	alarmtimer;
 		} alarm;
-		struct rcu_head		rcu;
 	} it;
+	struct rcu_head		rcu;
 };
 
-void run_posix_cpu_timers(struct task_struct *task);
+void run_posix_cpu_timers(void);
 void posix_cpu_timers_exit(struct task_struct *task);
 void posix_cpu_timers_exit_group(struct task_struct *task);
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f0edee94834a..b75b28287005 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -25,9 +25,11 @@
 #include <linux/resource.h>
 #include <linux/latencytop.h>
 #include <linux/sched/prio.h>
+#include <linux/sched/types.h>
 #include <linux/signal_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
+#include <linux/posix-timers.h>
 #include <linux/rseq.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -244,27 +246,6 @@ struct prev_cputime {
 #endif
 };
 
-/**
- * struct task_cputime - collected CPU time counts
- * @utime:		time spent in user mode, in nanoseconds
- * @stime:		time spent in kernel mode, in nanoseconds
- * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
- *
- * This structure groups together three kinds of CPU time that are tracked for
- * threads and thread groups.  Most things considering CPU time want to group
- * these counts together and treat all three of them in parallel.
- */
-struct task_cputime {
-	u64				utime;
-	u64				stime;
-	unsigned long long		sum_exec_runtime;
-};
-
-/* Alternate field names when used on cache expirations: */
-#define virt_exp			utime
-#define prof_exp			stime
-#define sched_exp			sum_exec_runtime
-
 enum vtime_state {
 	/* Task is sleeping or running in a CPU with VTIME inactive: */
 	VTIME_INACTIVE = 0,
@@ -881,10 +862,8 @@ struct task_struct {
 	unsigned long			min_flt;
 	unsigned long			maj_flt;
 
-#ifdef CONFIG_POSIX_TIMERS
-	struct task_cputime		cputime_expires;
-	struct list_head		cpu_timers[3];
-#endif
+	/* Empty if CONFIG_POSIX_CPUTIMERS=n */
+	struct posix_cputimers		posix_cputimers;
 
 	/* Process credentials: */
 
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 53f883f5a2fd..6c9f19a33865 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -61,8 +61,7 @@ extern void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
  * Thread group CPU time accounting.
  */
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
-void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
-
+void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples);
 
 /*
  * The following are functions that support scheduler-internal time accounting.
@@ -71,7 +70,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
  */
 
 /**
- * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimers are active
  *
  * @tsk:	Pointer to target task.
  */
@@ -81,8 +80,11 @@ struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
-	/* Check if cputimer isn't running. This is accessed without locking. */
-	if (!READ_ONCE(cputimer->running))
+	/*
+	 * Check whether posix CPU timers are active. If not the thread
+	 * group accounting is not active either. Lockless check.
+	 */
+	if (!READ_ONCE(tsk->signal->posix_cputimers.timers_active))
 		return NULL;
 
 	/*
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index efd8ce7675ed..88050259c466 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -9,6 +9,7 @@
 #include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/refcount.h>
+#include <linux/posix-timers.h>
 
 /*
  * Types defining task->signal and task->sighand and APIs using them:
@@ -56,18 +57,12 @@ struct task_cputime_atomic {
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime_atomic:	atomic thread group interval timers.
- * @running:		true when there are timers running and
- *			@cputime_atomic receives updates.
- * @checking_timer:	true when a thread in the group is in the
- *			process of checking for thread group timers.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
 	struct task_cputime_atomic cputime_atomic;
-	bool running;
-	bool checking_timer;
 };
 
 struct multiprocess_signals {
@@ -148,12 +143,9 @@ struct signal_struct {
 	 */
 	struct thread_group_cputimer cputimer;
 
-	/* Earliest-expiration cache. */
-	struct task_cputime cputime_expires;
-
-	struct list_head cpu_timers[3];
-
 #endif
+	/* Empty if CONFIG_POSIX_TIMERS=n */
+	struct posix_cputimers posix_cputimers;
 
 	/* PID/PID hash table linkage. */
 	struct pid *pids[PIDTYPE_MAX];
diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h
new file mode 100644
index 000000000000..3c3e049224ae
--- /dev/null
+++ b/include/linux/sched/types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TYPES_H
+#define _LINUX_SCHED_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * struct task_cputime - collected CPU time counts
+ * @stime:		time spent in kernel mode, in nanoseconds
+ * @utime:		time spent in user mode, in nanoseconds
+ * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
+ *
+ * This structure groups together three kinds of CPU time that are tracked for
+ * threads and thread groups.  Most things considering CPU time want to group
+ * these counts together and treat all three of them in parallel.
+ */
+struct task_cputime {
+	u64				stime;
+	u64				utime;
+	unsigned long long		sum_exec_runtime;
+};
+
+#endif
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 282e4f2a532a..1e6650ed066d 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -183,7 +183,7 @@ extern void add_timer(struct timer_list *timer);
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
   extern int del_timer_sync(struct timer_list *timer);
 #else
 # define del_timer_sync(t)		del_timer(t)
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index 78b8cc73f12f..93884086f392 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -12,8 +12,7 @@ struct timerqueue_node {
 };
 
 struct timerqueue_head {
-	struct rb_root head;
-	struct timerqueue_node *next;
+	struct rb_root_cached rb_root;
 };
 
 
@@ -29,13 +28,14 @@ extern struct timerqueue_node *timerqueue_iterate_next(
  *
  * @head: head of timerqueue
  *
- * Returns a pointer to the timer node that has the
- * earliest expiration time.
+ * Returns a pointer to the timer node that has the earliest expiration time.
  */
 static inline
 struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head)
 {
-	return head->next;
+	struct rb_node *leftmost = rb_first_cached(&head->rb_root);
+
+	return rb_entry(leftmost, struct timerqueue_node, node);
 }
 
 static inline void timerqueue_init(struct timerqueue_node *node)
@@ -43,9 +43,18 @@ static inline void timerqueue_init(struct timerqueue_node *node)
 	RB_CLEAR_NODE(&node->node);
 }
 
+static inline bool timerqueue_node_queued(struct timerqueue_node *node)
+{
+	return !RB_EMPTY_NODE(&node->node);
+}
+
+static inline bool timerqueue_node_expires(struct timerqueue_node *node)
+{
+	return node->expires;
+}
+
 static inline void timerqueue_init_head(struct timerqueue_head *head)
 {
-	head->head = RB_ROOT;
-	head->next = NULL;
+	head->rb_root = RB_ROOT_CACHED;
 }
 #endif /* _LINUX_TIMERQUEUE_H */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 30c515520fb2..3eb7cae8206c 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -501,8 +501,8 @@ do {										\
 	int __ret = 0;								\
 	struct hrtimer_sleeper __t;						\
 										\
-	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);	\
-	hrtimer_init_sleeper(&__t, current);					\
+	hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC,			\
+				      HRTIMER_MODE_REL);			\
 	if ((timeout) != KTIME_MAX)						\
 		hrtimer_start_range_ns(&__t.timer, timeout,			\
 				       current->timer_slack_ns,			\