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

Pull core timer updates from Ingo Molnar:
 "The main changes in this cycle's merge are:

   - Implement shadow timekeeper to shorten in kernel reader side
     blocking, by Thomas Gleixner.

   - Posix timers enhancements by Pavel Emelyanov:

   - allocate timer ID per process, so that exact timer ID allocations
     can be re-created be checkpoint/restore code.

   - debuggability and tooling (/proc/PID/timers, etc.) improvements.

   - suspend/resume enhancements by Feng Tang: on certain new Intel Atom
     processors (Penwell and Cloverview), there is a feature that the
     TSC won't stop in S3 state, so the TSC value won't be reset to 0
     after resume.  This can be taken advantage of by the generic via
     the CLOCK_SOURCE_SUSPEND_NONSTOP flag: instead of using the RTC to
     recover/approximate sleep time, the main (and precise) clocksource
     can be used.

   - Fix /proc/timer_list for 4096 CPUs by Nathan Zimmer: on so many
     CPUs the file goes beyond 4MB of size and thus the current
     simplistic seqfile approach fails.  Convert /proc/timer_list to a
     proper seq_file with its own iterator.

   - Cleanups and refactorings of the core timekeeping code by John
     Stultz.

   - International Atomic Clock time is managed by the NTP code
     internally currently but not exposed externally.  Separate the TAI
     code out and add CLOCK_TAI support and TAI support to the hrtimer
     and posix-timer code, by John Stultz.

   - Add deep idle support enhacement to the broadcast clockevents core
     timer code, by Daniel Lezcano: add an opt-in CLOCK_EVT_FEAT_DYNIRQ
     clockevents feature (which will be utilized by future clockevents
     driver updates), which allows the use of IRQ affinities to avoid
     spurious wakeups of idle CPUs - the right CPU with an expiring
     timer will be woken.

   - Add new ARM bcm281xx clocksource driver, by Christian Daudt

   - ... various other fixes and cleanups"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  clockevents: Set dummy handler on CPU_DEAD shutdown
  timekeeping: Update tk->cycle_last in resume
  posix-timers: Remove unused variable
  clockevents: Switch into oneshot mode even if broadcast registered late
  timer_list: Convert timer list to be a proper seq_file
  timer_list: Split timer_list_show_tickdevices
  posix-timers: Show sigevent info in proc file
  posix-timers: Introduce /proc/PID/timers file
  posix timers: Allocate timer id per process (v2)
  timekeeping: Make sure to notify hrtimers when TAI offset changes
  hrtimer: Fix ktime_add_ns() overflow on 32bit architectures
  hrtimer: Add expiry time overflow check in hrtimer_interrupt
  timekeeping: Shorten seq_count region
  timekeeping: Implement a shadow timekeeper
  timekeeping: Delay update of clock->cycle_last
  timekeeping: Store cycle_last value in timekeeper struct as well
  ntp: Remove ntp_lock, using the timekeeping locks to protect ntp state
  timekeeping: Simplify tai updating from do_adjtimex
  timekeeping: Hold timekeepering locks in do_adjtimex and hardpps
  timekeeping: Move ADJ_SETOFFSET to top level do_adjtimex()
  ...

12 files changed, 757 insertions, 279 deletions

diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 168cf407a25..8b86c0c68ed 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -76,7 +76,16 @@ static void cpu_idle_loop(void)
 			local_irq_disable();
 			arch_cpu_idle_enter();
 
-			if (cpu_idle_force_poll) {
+			/*
+			 * In poll mode we reenable interrupts and spin.
+			 *
+			 * Also if we detected in the wakeup from idle
+			 * path that the tick broadcast device expired
+			 * for us, we don't want to go deep idle as we
+			 * know that the IPI is going to arrive right
+			 * away
+			 */
+			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
 				current_clr_polling();
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 14be27feda4..609d8ff38b7 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -84,6 +84,12 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get_boottime,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = HRTIMER_BASE_TAI,
+			.clockid = CLOCK_TAI,
+			.get_time = &ktime_get_clocktai,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
@@ -91,6 +97,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
+	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
@@ -107,8 +114,10 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
 	ktime_t xtim, mono, boot;
 	struct timespec xts, tom, slp;
+	s32 tai_offset;
 
 	get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
+	tai_offset = timekeeping_get_tai_offset();
 
 	xtim = timespec_to_ktime(xts);
 	mono = ktime_add(xtim, timespec_to_ktime(tom));
@@ -116,6 +125,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
 	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
+	base->clock_base[HRTIMER_BASE_TAI].softirq_time =
+				ktime_add(xtim,	ktime_set(tai_offset, 0));
 }
 
 /*
@@ -276,6 +287,10 @@ ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
 	} else {
 		unsigned long rem = do_div(nsec, NSEC_PER_SEC);
 
+		/* Make sure nsec fits into long */
+		if (unlikely(nsec > KTIME_SEC_MAX))
+			return (ktime_t){ .tv64 = KTIME_MAX };
+
 		tmp = ktime_set((long)nsec, rem);
 	}
 
@@ -652,8 +667,9 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
 {
 	ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
 	ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+	ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
 
-	return ktime_get_update_offsets(offs_real, offs_boot);
+	return ktime_get_update_offsets(offs_real, offs_boot, offs_tai);
 }
 
 /*
@@ -1011,7 +1027,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
  * @timer:	the timer to be added
  * @tim:	expiry time
  * @delta_ns:	"slack" range for the timer
- * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
  *
  * Returns:
  *  0 on success
@@ -1028,7 +1045,8 @@ EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
  * hrtimer_start - (re)start an hrtimer on the current CPU
  * @timer:	the timer to be added
  * @tim:	expiry time
- * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL)
  *
  * Returns:
  *  0 on success
@@ -1310,6 +1328,8 @@ retry:
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
 						    base->offset);
+				if (expires.tv64 < 0)
+					expires.tv64 = KTIME_MAX;
 				if (expires.tv64 < expires_next.tv64)
 					expires_next = expires;
 				break;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 6edbb2c55c2..424c2d4265c 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -40,38 +40,31 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
-#include <linux/idr.h>
+#include <linux/hash.h>
 #include <linux/posix-clock.h>
 #include <linux/posix-timers.h>
 #include <linux/syscalls.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/export.h>
+#include <linux/hashtable.h>
 
 /*
- * Management arrays for POSIX timers.	 Timers are kept in slab memory
- * Timer ids are allocated by an external routine that keeps track of the
- * id and the timer.  The external interface is:
- *
- * void *idr_find(struct idr *idp, int id);           to find timer_id <id>
- * int idr_get_new(struct idr *idp, void *ptr);       to get a new id and
- *                                                    related it to <ptr>
- * void idr_remove(struct idr *idp, int id);          to release <id>
- * void idr_init(struct idr *idp);                    to initialize <idp>
- *                                                    which we supply.
- * The idr_get_new *may* call slab for more memory so it must not be
- * called under a spin lock.  Likewise idr_remore may release memory
- * (but it may be ok to do this under a lock...).
- * idr_find is just a memory look up and is quite fast.  A -1 return
- * indicates that the requested id does not exist.
+ * Management arrays for POSIX timers. Timers are now kept in static hash table
+ * with 512 entries.
+ * Timer ids are allocated by local routine, which selects proper hash head by
+ * key, constructed from current->signal address and per signal struct counter.
+ * This keeps timer ids unique per process, but now they can intersect between
+ * processes.
  */
 
 /*
  * Lets keep our timers in a slab cache :-)
  */
 static struct kmem_cache *posix_timers_cache;
-static struct idr posix_timers_id;
-static DEFINE_SPINLOCK(idr_lock);
+
+static DEFINE_HASHTABLE(posix_timers_hashtable, 9);
+static DEFINE_SPINLOCK(hash_lock);
 
 /*
  * we assume that the new SIGEV_THREAD_ID shares no bits with the other
@@ -152,6 +145,56 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);
 	__timr;								   \
 })
 
+static int hash(struct signal_struct *sig, unsigned int nr)
+{
+	return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable));
+}
+
+static struct k_itimer *__posix_timers_find(struct hlist_head *head,
+					    struct signal_struct *sig,
+					    timer_t id)
+{
+	struct k_itimer *timer;
+
+	hlist_for_each_entry_rcu(timer, head, t_hash) {
+		if ((timer->it_signal == sig) && (timer->it_id == id))
+			return timer;
+	}
+	return NULL;
+}
+
+static struct k_itimer *posix_timer_by_id(timer_t id)
+{
+	struct signal_struct *sig = current->signal;
+	struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)];
+
+	return __posix_timers_find(head, sig, id);
+}
+
+static int posix_timer_add(struct k_itimer *timer)
+{
+	struct signal_struct *sig = current->signal;
+	int first_free_id = sig->posix_timer_id;
+	struct hlist_head *head;
+	int ret = -ENOENT;
+
+	do {
+		spin_lock(&hash_lock);
+		head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)];
+		if (!__posix_timers_find(head, sig, sig->posix_timer_id)) {
+			hlist_add_head_rcu(&timer->t_hash, head);
+			ret = sig->posix_timer_id;
+		}
+		if (++sig->posix_timer_id < 0)
+			sig->posix_timer_id = 0;
+		if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT))
+			/* Loop over all possible ids completed */
+			ret = -EAGAIN;
+		spin_unlock(&hash_lock);
+	} while (ret == -ENOENT);
+	return ret;
+}
+
 static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
 {
 	spin_unlock_irqrestore(&timr->it_lock, flags);
@@ -221,6 +264,11 @@ static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+{
+	timekeeping_clocktai(tp);
+	return 0;
+}
 
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
@@ -261,6 +309,16 @@ static __init int init_posix_timers(void)
 		.clock_getres	= posix_get_coarse_res,
 		.clock_get	= posix_get_monotonic_coarse,
 	};
+	struct k_clock clock_tai = {
+		.clock_getres	= hrtimer_get_res,
+		.clock_get	= posix_get_tai,
+		.nsleep		= common_nsleep,
+		.nsleep_restart	= hrtimer_nanosleep_restart,
+		.timer_create	= common_timer_create,
+		.timer_set	= common_timer_set,
+		.timer_get	= common_timer_get,
+		.timer_del	= common_timer_del,
+	};
 	struct k_clock clock_boottime = {
 		.clock_getres	= hrtimer_get_res,
 		.clock_get	= posix_get_boottime,
@@ -278,11 +336,11 @@ static __init int init_posix_timers(void)
 	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
 	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
 	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
+	posix_timers_register_clock(CLOCK_TAI, &clock_tai);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
 					NULL);
-	idr_init(&posix_timers_id);
 	return 0;
 }
 
@@ -504,9 +562,9 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 {
 	if (it_id_set) {
 		unsigned long flags;
-		spin_lock_irqsave(&idr_lock, flags);
-		idr_remove(&posix_timers_id, tmr->it_id);
-		spin_unlock_irqrestore(&idr_lock, flags);
+		spin_lock_irqsave(&hash_lock, flags);
+		hlist_del_rcu(&tmr->t_hash);
+		spin_unlock_irqrestore(&hash_lock, flags);
 	}
 	put_pid(tmr->it_pid);
 	sigqueue_free(tmr->sigq);
@@ -552,22 +610,11 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		return -EAGAIN;
 
 	spin_lock_init(&new_timer->it_lock);
-
-	idr_preload(GFP_KERNEL);
-	spin_lock_irq(&idr_lock);
-	error = idr_alloc(&posix_timers_id, new_timer, 0, 0, GFP_NOWAIT);
-	spin_unlock_irq(&idr_lock);
-	idr_preload_end();
-	if (error < 0) {
-		/*
-		 * Weird looking, but we return EAGAIN if the IDR is
-		 * full (proper POSIX return value for this)
-		 */
-		if (error == -ENOSPC)
-			error = -EAGAIN;
+	new_timer_id = posix_timer_add(new_timer);
+	if (new_timer_id < 0) {
+		error = new_timer_id;
 		goto out;
 	}
-	new_timer_id = error;
 
 	it_id_set = IT_ID_SET;
 	new_timer->it_id = (timer_t) new_timer_id;
@@ -645,7 +692,7 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
 		return NULL;
 
 	rcu_read_lock();
-	timr = idr_find(&posix_timers_id, (int)timer_id);
+	timr = posix_timer_by_id(timer_id);
 	if (timr) {
 		spin_lock_irqsave(&timr->it_lock, *flags);
 		if (timr->it_signal == current->signal) {
diff --git a/kernel/time.c b/kernel/time.c
index f8342a41efa..d3617dbd3dc 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -138,13 +138,14 @@ int persistent_clock_is_local;
  */
 static inline void warp_clock(void)
 {
-	struct timespec adjust;
+	if (sys_tz.tz_minuteswest != 0) {
+		struct timespec adjust;
 
-	adjust = current_kernel_time();
-	if (sys_tz.tz_minuteswest != 0)
 		persistent_clock_is_local = 1;
-	adjust.tv_sec += sys_tz.tz_minuteswest * 60;
-	do_settimeofday(&adjust);
+		adjust.tv_sec = sys_tz.tz_minuteswest * 60;
+		adjust.tv_nsec = 0;
+		timekeeping_inject_offset(&adjust);
+	}
 }
 
 /*
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 072bb066bb7..12ff13a838c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -18,13 +18,14 @@
 #include <linux/rtc.h>
 
 #include "tick-internal.h"
+#include "ntp_internal.h"
 
 /*
  * NTP timekeeping variables:
+ *
+ * Note: All of the NTP state is protected by the timekeeping locks.
  */
 
-DEFINE_RAW_SPINLOCK(ntp_lock);
-
 
 /* USER_HZ period (usecs): */
 unsigned long			tick_usec = TICK_USEC;
@@ -53,9 +54,6 @@ static int			time_state = TIME_OK;
 /* clock status bits:							*/
 static int			time_status = STA_UNSYNC;
 
-/* TAI offset (secs):							*/
-static long			time_tai;
-
 /* time adjustment (nsecs):						*/
 static s64			time_offset;
 
@@ -134,8 +132,6 @@ static inline void pps_reset_freq_interval(void)
 
 /**
  * pps_clear - Clears the PPS state variables
- *
- * Must be called while holding a write on the ntp_lock
  */
 static inline void pps_clear(void)
 {
@@ -150,8 +146,6 @@ static inline void pps_clear(void)
 /* Decrease pps_valid to indicate that another second has passed since
  * the last PPS signal. When it reaches 0, indicate that PPS signal is
  * missing.
- *
- * Must be called while holding a write on the ntp_lock
  */
 static inline void pps_dec_valid(void)
 {
@@ -346,10 +340,6 @@ static void ntp_update_offset(long offset)
  */
 void ntp_clear(void)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&ntp_lock, flags);
-
 	time_adjust	= 0;		/* stop active adjtime() */
 	time_status	|= STA_UNSYNC;
 	time_maxerror	= NTP_PHASE_LIMIT;
@@ -362,20 +352,12 @@ void ntp_clear(void)
 
 	/* Clear PPS state variables */
 	pps_clear();
-	raw_spin_unlock_irqrestore(&ntp_lock, flags);
-
 }
 
 
 u64 ntp_tick_length(void)
 {
-	unsigned long flags;
-	s64 ret;
-
-	raw_spin_lock_irqsave(&ntp_lock, flags);
-	ret = tick_length;
-	raw_spin_unlock_irqrestore(&ntp_lock, flags);
-	return ret;
+	return tick_length;
 }
 
 
@@ -393,9 +375,6 @@ int second_overflow(unsigned long secs)
 {
 	s64 delta;
 	int leap = 0;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&ntp_lock, flags);
 
 	/*
 	 * Leap second processing. If in leap-insert state at the end of the
@@ -415,7 +394,6 @@ int second_overflow(unsigned long secs)
 		else if (secs % 86400 == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
-			time_tai++;
 			printk(KERN_NOTICE
 				"Clock: inserting leap second 23:59:60 UTC\n");
 		}
@@ -425,7 +403,6 @@ int second_overflow(unsigned long secs)
 			time_state = TIME_OK;
 		else if ((secs + 1) % 86400 == 0) {
 			leap = 1;
-			time_tai--;
 			time_state = TIME_WAIT;
 			printk(KERN_NOTICE
 				"Clock: deleting leap second 23:59:59 UTC\n");
@@ -479,8 +456,6 @@ int second_overflow(unsigned long secs)
 	time_adjust = 0;
 
 out:
-	raw_spin_unlock_irqrestore(&ntp_lock, flags);
-
 	return leap;
 }
 
@@ -575,11 +550,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
 	time_status |= txc->status & ~STA_RONLY;
 }
 
-/*
- * Called with ntp_lock held, so we can access and modify
- * all the global NTP state:
- */
-static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
+
+static inline void process_adjtimex_modes(struct timex *txc,
+						struct timespec *ts,
+						s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
 		process_adj_status(txc, ts);
@@ -613,7 +587,7 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
 	}
 
 	if (txc->modes & ADJ_TAI && txc->constant > 0)
-		time_tai = txc->constant;
+		*time_tai = txc->constant;
 
 	if (txc->modes & ADJ_OFFSET)
 		ntp_update_offset(txc->offset);
@@ -625,16 +599,13 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
 		ntp_update_frequency();
 }
 
-/*
- * adjtimex mainly allows reading (and writing, if superuser) of
- * kernel time-keeping variables. used by xntpd.
+
+
+/**
+ * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex
  */
-int do_adjtimex(struct timex *txc)
+int ntp_validate_timex(struct timex *txc)
 {
-	struct timespec ts;
-	int result;
-
-	/* Validate the data before disabling interrupts */
 	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
 		if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
@@ -646,7 +617,6 @@ int do_adjtimex(struct timex *txc)
 		/* In order to modify anything, you gotta be super-user! */
 		 if (txc->modes && !capable(CAP_SYS_TIME))
 			return -EPERM;
-
 		/*
 		 * if the quartz is off by more than 10% then
 		 * something is VERY wrong!
@@ -657,22 +627,20 @@ int do_adjtimex(struct timex *txc)
 			return -EINVAL;
 	}
 
-	if (txc->modes & ADJ_SETOFFSET) {
-		struct timespec delta;
-		delta.tv_sec  = txc->time.tv_sec;
-		delta.tv_nsec = txc->time.tv_usec;
-		if (!capable(CAP_SYS_TIME))
-			return -EPERM;
-		if (!(txc->modes & ADJ_NANO))
-			delta.tv_nsec *= 1000;
-		result = timekeeping_inject_offset(&delta);
-		if (result)
-			return result;
-	}
+	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
+		return -EPERM;
 
-	getnstimeofday(&ts);
+	return 0;
+}
 
-	raw_spin_lock_irq(&ntp_lock);
+
+/*
+ * adjtimex mainly allows reading (and writing, if superuser) of
+ * kernel time-keeping variables. used by xntpd.
+ */
+int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
+{
+	int result;
 
 	if (txc->modes & ADJ_ADJTIME) {
 		long save_adjust = time_adjust;
@@ -687,7 +655,7 @@ int do_adjtimex(struct timex *txc)
 
 		/* If there are input parameters, then process them: */
 		if (txc->modes)
-			process_adjtimex_modes(txc, &ts);
+			process_adjtimex_modes(txc, ts, time_tai);
 
 		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
@@ -709,15 +677,13 @@ int do_adjtimex(struct timex *txc)
 	txc->precision	   = 1;
 	txc->tolerance	   = MAXFREQ_SCALED / PPM_SCALE;
 	txc->tick	   = tick_usec;
-	txc->tai	   = time_tai;
+	txc->tai	   = *time_tai;
 
 	/* fill PPS status fields */
 	pps_fill_timex(txc);
 
-	raw_spin_unlock_irq(&ntp_lock);
-
-	txc->time.tv_sec = ts.tv_sec;
-	txc->time.tv_usec = ts.tv_nsec;
+	txc->time.tv_sec = ts->tv_sec;
+	txc->time.tv_usec = ts->tv_nsec;
 	if (!(time_status & STA_NANO))
 		txc->time.tv_usec /= NSEC_PER_USEC;
 
@@ -894,7 +860,7 @@ static void hardpps_update_phase(long error)
 }
 
 /*
- * hardpps() - discipline CPU clock oscillator to external PPS signal
+ * __hardpps() - discipline CPU clock oscillator to external PPS signal
  *
  * This routine is called at each PPS signal arrival in order to
  * discipline the CPU clock oscillator to the PPS signal. It takes two
@@ -905,15 +871,13 @@ static void hardpps_update_phase(long error)
  * This code is based on David Mills's reference nanokernel
  * implementation. It was mostly rewritten but keeps the same idea.
  */
-void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 {
 	struct pps_normtime pts_norm, freq_norm;
 	unsigned long flags;
 
 	pts_norm = pps_normalize_ts(*phase_ts);
 
-	raw_spin_lock_irqsave(&ntp_lock, flags);
-
 	/* clear the error bits, they will be set again if needed */
 	time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
 
@@ -925,7 +889,6 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 	 * just start the frequency interval */
 	if (unlikely(pps_fbase.tv_sec == 0)) {
 		pps_fbase = *raw_ts;
-		raw_spin_unlock_irqrestore(&ntp_lock, flags);
 		return;
 	}
 
@@ -940,7 +903,6 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 		time_status |= STA_PPSJITTER;
 		/* restart the frequency calibration interval */
 		pps_fbase = *raw_ts;
-		raw_spin_unlock_irqrestore(&ntp_lock, flags);
 		pr_err("hardpps: PPSJITTER: bad pulse\n");
 		return;
 	}
@@ -957,10 +919,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
 
 	hardpps_update_phase(pts_norm.nsec);
 
-	raw_spin_unlock_irqrestore(&ntp_lock, flags);
 }
-EXPORT_SYMBOL(hardpps);
-
 #endif	/* CONFIG_NTP_PPS */
 
 static int __init ntp_tick_adj_setup(char *str)
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
new file mode 100644
index 00000000000..1950cb4ca2a
--- /dev/null
+++ b/kernel/time/ntp_internal.h
@@ -0,0 +1,12 @@
+#ifndef _LINUX_NTP_INTERNAL_H
+#define _LINUX_NTP_INTERNAL_H
+
+extern void ntp_init(void);
+extern void ntp_clear(void);
+/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
+extern u64 ntp_tick_length(void);
+extern int second_overflow(unsigned long secs);
+extern int ntp_validate_timex(struct timex *);
+extern int __do_adjtimex(struct timex *, struct timespec *, s32 *);
+extern void __hardpps(const struct timespec *, const struct timespec *);
+#endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 7f32fe0e52c..61d00a8cdf2 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -28,9 +28,8 @@
  */
 
 static struct tick_device tick_broadcast_device;
-/* FIXME: Use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
-static DECLARE_BITMAP(tmpmask, NR_CPUS);
+static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tmpmask;
 static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static int tick_broadcast_force;
 
@@ -50,7 +49,7 @@ struct tick_device *tick_get_broadcast_device(void)
 
 struct cpumask *tick_get_broadcast_mask(void)
 {
-	return to_cpumask(tick_broadcast_mask);
+	return tick_broadcast_mask;
 }
 
 /*
@@ -67,6 +66,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
+	struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
 	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
 	    (tick_broadcast_device.evtdev &&
 	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
@@ -74,9 +75,21 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 		return 0;
 
 	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	if (cur)
+		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
-	if (!cpumask_empty(tick_get_broadcast_mask()))
+	if (!cpumask_empty(tick_broadcast_mask))
 		tick_broadcast_start_periodic(dev);
+	/*
+	 * Inform all cpus about this. We might be in a situation
+	 * where we did not switch to oneshot mode because the per cpu
+	 * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack
+	 * of a oneshot capable broadcast device. Without that
+	 * notification the systems stays stuck in periodic mode
+	 * forever.
+	 */
+	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_clock_notify();
 	return 1;
 }
 
@@ -124,7 +137,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 	if (!tick_device_is_functional(dev)) {
 		dev->event_handler = tick_handle_periodic;
 		tick_device_setup_broadcast_func(dev);
-		cpumask_set_cpu(cpu, tick_get_broadcast_mask());
+		cpumask_set_cpu(cpu, tick_broadcast_mask);
 		tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
 		ret = 1;
 	} else {
@@ -135,7 +148,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 		 */
 		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
 			int cpu = smp_processor_id();
-			cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+			cpumask_clear_cpu(cpu, tick_broadcast_mask);
 			tick_broadcast_clear_oneshot(cpu);
 		} else {
 			tick_device_setup_broadcast_func(dev);
@@ -199,9 +212,8 @@ static void tick_do_periodic_broadcast(void)
 {
 	raw_spin_lock(&tick_broadcast_lock);
 
-	cpumask_and(to_cpumask(tmpmask),
-		    cpu_online_mask, tick_get_broadcast_mask());
-	tick_do_broadcast(to_cpumask(tmpmask));
+	cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
+	tick_do_broadcast(tmpmask);
 
 	raw_spin_unlock(&tick_broadcast_lock);
 }
@@ -264,13 +276,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 	if (!tick_device_is_functional(dev))
 		goto out;
 
-	bc_stopped = cpumask_empty(tick_get_broadcast_mask());
+	bc_stopped = cpumask_empty(tick_broadcast_mask);
 
 	switch (*reason) {
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
-			cpumask_set_cpu(cpu, tick_get_broadcast_mask());
+		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
@@ -280,8 +291,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 		break;
 	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
 		if (!tick_broadcast_force &&
-		    cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
-			cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+		    cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
@@ -289,7 +299,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
 		break;
 	}
 
-	if (cpumask_empty(tick_get_broadcast_mask())) {
+	if (cpumask_empty(tick_broadcast_mask)) {
 		if (!bc_stopped)
 			clockevents_shutdown(bc);
 	} else if (bc_stopped) {
@@ -338,10 +348,10 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
-	cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+	cpumask_clear_cpu(cpu, tick_broadcast_mask);
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
-		if (bc && cpumask_empty(tick_get_broadcast_mask()))
+		if (bc && cpumask_empty(tick_broadcast_mask))
 			clockevents_shutdown(bc);
 	}
 
@@ -377,13 +387,13 @@ int tick_resume_broadcast(void)
 
 		switch (tick_broadcast_device.mode) {
 		case TICKDEV_MODE_PERIODIC:
-			if (!cpumask_empty(tick_get_broadcast_mask()))
+			if (!cpumask_empty(tick_broadcast_mask))
 				tick_broadcast_start_periodic(bc);
 			broadcast = cpumask_test_cpu(smp_processor_id(),
-						     tick_get_broadcast_mask());
+						     tick_broadcast_mask);
 			break;
 		case TICKDEV_MODE_ONESHOT:
-			if (!cpumask_empty(tick_get_broadcast_mask()))
+			if (!cpumask_empty(tick_broadcast_mask))
 				broadcast = tick_resume_broadcast_oneshot(bc);
 			break;
 		}
@@ -396,25 +406,58 @@ int tick_resume_broadcast(void)
 
 #ifdef CONFIG_TICK_ONESHOT
 
-/* FIXME: use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS);
+static cpumask_var_t tick_broadcast_oneshot_mask;
+static cpumask_var_t tick_broadcast_pending_mask;
+static cpumask_var_t tick_broadcast_force_mask;
 
 /*
  * Exposed for debugging: see timer_list.c
  */
 struct cpumask *tick_get_broadcast_oneshot_mask(void)
 {
-	return to_cpumask(tick_broadcast_oneshot_mask);
+	return tick_broadcast_oneshot_mask;
 }
 
-static int tick_broadcast_set_event(ktime_t expires, int force)
+/*
+ * Called before going idle with interrupts disabled. Checks whether a
+ * broadcast event from the other core is about to happen. We detected
+ * that in tick_broadcast_oneshot_control(). The callsite can use this
+ * to avoid a deep idle transition as we are about to get the
+ * broadcast IPI right away.
+ */
+int tick_check_broadcast_expired(void)
 {
-	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+	return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask);
+}
+
+/*
+ * Set broadcast interrupt affinity
+ */
+static void tick_broadcast_set_affinity(struct clock_event_device *bc,
+					const struct cpumask *cpumask)
+{
+	if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
+		return;
+
+	if (cpumask_equal(bc->cpumask, cpumask))
+		return;
+
+	bc->cpumask = cpumask;
+	irq_set_affinity(bc->irq, bc->cpumask);
+}
+
+static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+				    ktime_t expires, int force)
+{
+	int ret;
 
 	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 
-	return clockevents_program_event(bc, expires, force);
+	ret = clockevents_program_event(bc, expires, force);
+	if (!ret)
+		tick_broadcast_set_affinity(bc, cpumask_of(cpu));
+	return ret;
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -429,7 +472,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  */
 void tick_check_oneshot_broadcast(int cpu)
 {
-	if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
+	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
 		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 
 		clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
@@ -443,27 +486,39 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 {
 	struct tick_device *td;
 	ktime_t now, next_event;
-	int cpu;
+	int cpu, next_cpu = 0;
 
 	raw_spin_lock(&tick_broadcast_lock);
 again:
 	dev->next_event.tv64 = KTIME_MAX;
 	next_event.tv64 = KTIME_MAX;
-	cpumask_clear(to_cpumask(tmpmask));
+	cpumask_clear(tmpmask);
 	now = ktime_get();
 	/* Find all expired events */
-	for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) {
+	for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
 		td = &per_cpu(tick_cpu_device, cpu);
-		if (td->evtdev->next_event.tv64 <= now.tv64)
-			cpumask_set_cpu(cpu, to_cpumask(tmpmask));
-		else if (td->evtdev->next_event.tv64 < next_event.tv64)
+		if (td->evtdev->next_event.tv64 <= now.tv64) {
+			cpumask_set_cpu(cpu, tmpmask);
+			/*
+			 * Mark the remote cpu in the pending mask, so
+			 * it can avoid reprogramming the cpu local
+			 * timer in tick_broadcast_oneshot_control().
+			 */
+			cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
+		} else if (td->evtdev->next_event.tv64 < next_event.tv64) {
 			next_event.tv64 = td->evtdev->next_event.tv64;
+			next_cpu = cpu;
+		}
 	}
 
+	/* Take care of enforced broadcast requests */
+	cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
+	cpumask_clear(tick_broadcast_force_mask);
+
 	/*
 	 * Wakeup the cpus which have a