timers for 3.7

Linus,

please pull the latest timers-core-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-core-for-linus

------------------>
Arnd Bergmann (1):
time/jiffies: bring back unconditional LATCH definition

Dan Carpenter (1):
timekeeping: Cast raw_interval to u64 to avoid shift overflow

Hildner, Christian (1):
timers: Fix endless looping between cascade() and internal_add_timer()

John Stultz (11):
alarmtimer: Use hrtimer per-alarm instead of per-base
alarmtimer: Remove unused helpers & defines
alarmtimer: Rename alarmtimer_remove to alarmtimer_dequeue
jiffies: Kill unused TICK_USEC_TO_NSEC
jiffies: Remove compile time assumptions about CLOCK_TICK_RATE
time: Move timekeeper structure to timekeeper_internal.h for vsyscall changes
time: Move update_vsyscall definitions to timekeeper_internal.h
time: Convert CONFIG_GENERIC_TIME_VSYSCALL to CONFIG_GENERIC_TIME_VSYSCALL_OLD
time: Introduce new GENERIC_TIME_VSYSCALL
time: Only do nanosecond rounding on GENERIC_TIME_VSYSCALL_OLD systems
time: Convert x86_64 to using new update_vsyscall

Tejun Heo (4):
timer: Generalize timer->base flags handling
timer: Relocate declarations of init_timer_on_stack_key()
timer: Clean up timer initializers
timer: Implement TIMER_IRQSAFE

Todd Poynor (1):
alarmtimer: Implement minimum alarm interval for allowing suspend

 arch/ia64/Kconfig                   |    2 +-
 arch/ia64/kernel/time.c             |    4 +-
 arch/powerpc/Kconfig                |    2 +-
 arch/powerpc/kernel/time.c          |    4 +-
 arch/s390/Kconfig                   |    2 +-
 arch/s390/kernel/time.c             |    4 +-
 arch/x86/include/asm/vgtod.h        |    4 +-
 arch/x86/kernel/setup.c             |    3 +
 arch/x86/kernel/vsyscall_64.c       |   49 ++++++----
 arch/x86/vdso/vclock_gettime.c      |   22 +++--
 include/linux/alarmtimer.h          |   31 +------
 include/linux/clocksource.h         |   16 ----
 include/linux/jiffies.h             |   20 +----
 include/linux/timekeeper_internal.h |  108 +++++++++++++++++++++++
 include/linux/timer.h               |  165 ++++++++++++++---------------------
 kernel/time.c                       |    2 +-
 kernel/time/Kconfig                 |    4 +
 kernel/time/alarmtimer.c            |  118 +++++++++----------------
 kernel/time/jiffies.c               |   32 +++++++-
 kernel/time/timekeeping.c           |  117 +++++++------------------
 kernel/timer.c                      |  118 ++++++++++++-------------
 21 files changed, 403 insertions(+), 424 deletions(-)
 create mode 100644 include/linux/timekeeper_internal.h

arch/ia64/Kconfig +1 -1

index 310cf57..f9e673c 100644
@@ -38,7 +38,7 @@ config IA64
 	select ARCH_TASK_STRUCT_ALLOCATOR
 	select ARCH_THREAD_INFO_ALLOCATOR
 	select ARCH_CLOCKSOURCE_DATA
-	select GENERIC_TIME_VSYSCALL
+	select GENERIC_TIME_VSYSCALL_OLD
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to

arch/ia64/kernel/time.c +2 -2

index ecc904b..d2f4e26 100644
@@ -19,7 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/efi.h>
 #include <linux/timex.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/platform_device.h>
 
 #include <asm/machvec.h>

@@ -454,7 +454,7 @@ void update_vsyscall_tz(void)
 {
 }
 
-void update_vsyscall(struct timespec *wall, struct timespec *wtm,
+void update_vsyscall_old(struct timespec *wall, struct timespec *wtm,
 			struct clocksource *c, u32 mult)
 {
 	write_seqcount_begin(&fsyscall_gtod_data.seq);

arch/powerpc/Kconfig +1 -1

index 352f416..0881660 100644
@@ -135,7 +135,7 @@ config PPC
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
-	select GENERIC_TIME_VSYSCALL
+	select GENERIC_TIME_VSYSCALL_OLD
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER

arch/powerpc/kernel/time.c +2 -2

index e49e931..c825809 100644
@@ -73,7 +73,7 @@
 /* powerpc clocksource/clockevent code */
 
 #include <linux/clockchips.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 
 static cycle_t rtc_read(struct clocksource *);
 static struct clocksource clocksource_rtc = {

@@ -712,7 +712,7 @@ static cycle_t timebase_read(struct clocksource *cs)
 	return (cycle_t)get_tb();
 }
 
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
+void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
 	u64 new_tb_to_xs, new_stamp_xsec;

arch/s390/Kconfig +1 -1

index 107610e..ba488aa 100644
@@ -121,7 +121,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_TIME_VSYSCALL
+	select GENERIC_TIME_VSYSCALL_OLD
 	select GENERIC_CLOCKEVENTS
 	select KTIME_SCALAR if 32BIT
 	select HAVE_ARCH_SECCOMP_FILTER

arch/s390/kernel/time.c +2 -2

index dcec960..c5430bf 100644
@@ -34,7 +34,7 @@
 #include <linux/profile.h>
 #include <linux/timex.h>
 #include <linux/notifier.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/clockchips.h>
 #include <linux/gfp.h>
 #include <linux/kprobes.h>

@@ -219,7 +219,7 @@ struct clocksource * __init clocksource_default_clock(void)
 	return &clocksource_tod;
 }
 
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
+void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
 	if (clock != &clocksource_tod)

arch/x86/include/asm/vgtod.h +2 -2

index 8b38be2..46e24d3 100644
@@ -17,8 +17,8 @@ struct vsyscall_gtod_data {
 
 	/* open coded 'struct timespec' */
 	time_t		wall_time_sec;
-	u32		wall_time_nsec;
-	u32		monotonic_time_nsec;
+	u64		wall_time_snsec;
+	u64		monotonic_time_snsec;
 	time_t		monotonic_time_sec;
 
 	struct timezone sys_tz;

arch/x86/kernel/setup.c +3 -0

index f4b9b80..4062f15 100644
@@ -68,6 +68,7 @@
 #include <linux/percpu.h>
 #include <linux/crash_dump.h>
 #include <linux/tboot.h>
+#include <linux/jiffies.h>
 
 #include <video/edid.h>
 

@@ -1034,6 +1035,8 @@ void __init setup_arch(char **cmdline_p)
 	mcheck_init();
 
 	arch_init_ideal_nops();
+
+	register_refined_jiffies(CLOCK_TICK_RATE);
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/vsyscall_64.c +29 -20

index 8d141b3..3a3e8c9 100644
@@ -28,7 +28,7 @@
 #include <linux/jiffies.h>
 #include <linux/sysctl.h>
 #include <linux/topology.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/getcpu.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>

@@ -82,32 +82,41 @@ void update_vsyscall_tz(void)
 	vsyscall_gtod_data.sys_tz = sys_tz;
 }
 
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
-			struct clocksource *clock, u32 mult)
+void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec monotonic;
+	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
 
-	write_seqcount_begin(&vsyscall_gtod_data.seq);
+	write_seqcount_begin(&vdata->seq);
 
 	/* copy vsyscall data */
-	vsyscall_gtod_data.clock.vclock_mode	= clock->archdata.vclock_mode;
-	vsyscall_gtod_data.clock.cycle_last	= clock->cycle_last;
-	vsyscall_gtod_data.clock.mask		= clock->mask;
-	vsyscall_gtod_data.clock.mult		= mult;
-	vsyscall_gtod_data.clock.shift		= clock->shift;
-
-	vsyscall_gtod_data.wall_time_sec	= wall_time->tv_sec;
-	vsyscall_gtod_data.wall_time_nsec	= wall_time->tv_nsec;
+	vdata->clock.vclock_mode	= tk->clock->archdata.vclock_mode;
+	vdata->clock.cycle_last		= tk->clock->cycle_last;
+	vdata->clock.mask		= tk->clock->mask;
+	vdata->clock.mult		= tk->mult;
+	vdata->clock.shift		= tk->shift;
+
+	vdata->wall_time_sec		= tk->xtime_sec;
+	vdata->wall_time_snsec		= tk->xtime_nsec;
+
+	vdata->monotonic_time_sec	= tk->xtime_sec
+					+ tk->wall_to_monotonic.tv_sec;
+	vdata->monotonic_time_snsec	= tk->xtime_nsec
+					+ (tk->wall_to_monotonic.tv_nsec
+						<< tk->shift);
+	while (vdata->monotonic_time_snsec >=
+					(((u64)NSEC_PER_SEC) << tk->shift)) {
+		vdata->monotonic_time_snsec -=
+					((u64)NSEC_PER_SEC) << tk->shift;
+		vdata->monotonic_time_sec++;
+	}
 
-	monotonic = timespec_add(*wall_time, *wtm);
-	vsyscall_gtod_data.monotonic_time_sec	= monotonic.tv_sec;
-	vsyscall_gtod_data.monotonic_time_nsec	= monotonic.tv_nsec;
+	vdata->wall_time_coarse.tv_sec	= tk->xtime_sec;
+	vdata->wall_time_coarse.tv_nsec	= (long)(tk->xtime_nsec >> tk->shift);
 
-	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
-	vsyscall_gtod_data.monotonic_time_coarse =
-		timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
+	vdata->monotonic_time_coarse	= timespec_add(vdata->wall_time_coarse,
+							tk->wall_to_monotonic);
 
-	write_seqcount_end(&vsyscall_gtod_data.seq);
+	write_seqcount_end(&vdata->seq);
 }
 
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,

arch/x86/vdso/vclock_gettime.c +14 -8

index 885eff4..4df6c37 100644
@@ -80,7 +80,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 }
 
 
-notrace static inline long vgetns(void)
+notrace static inline u64 vgetsns(void)
 {
 	long v;
 	cycles_t cycles;

@@ -91,21 +91,24 @@ notrace static inline long vgetns(void)
 	else
 		return 0;
 	v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
-	return (v * gtod->clock.mult) >> gtod->clock.shift;
+	return v * gtod->clock.mult;
 }
 
 /* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
 notrace static int __always_inline do_realtime(struct timespec *ts)
 {
-	unsigned long seq, ns;
+	unsigned long seq;
+	u64 ns;
 	int mode;
 
+	ts->tv_nsec = 0;
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
-		ts->tv_nsec = gtod->wall_time_nsec;
-		ns = vgetns();
+		ns = gtod->wall_time_snsec;
+		ns += vgetsns();
+		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
 	timespec_add_ns(ts, ns);

@@ -114,15 +117,18 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 notrace static int do_monotonic(struct timespec *ts)
 {
-	unsigned long seq, ns;
+	unsigned long seq;
+	u64 ns;
 	int mode;
 
+	ts->tv_nsec = 0;
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
-		ts->tv_nsec = gtod->monotonic_time_nsec;
-		ns = vgetns();
+		ns = gtod->monotonic_time_snsec;
+		ns += vgetsns();
+		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	timespec_add_ns(ts, ns);
 

include/linux/alarmtimer.h +2 -29

index 96c5c24..9069694 100644
@@ -21,7 +21,6 @@ enum alarmtimer_restart {
 
 #define ALARMTIMER_STATE_INACTIVE	0x00
 #define ALARMTIMER_STATE_ENQUEUED	0x01
-#define ALARMTIMER_STATE_CALLBACK	0x02
 
 /**
  * struct alarm - Alarm timer structure

@@ -35,6 +34,7 @@ enum alarmtimer_restart {
  */
 struct alarm {
 	struct timerqueue_node	node;
+	struct hrtimer		timer;
 	enum alarmtimer_restart	(*function)(struct alarm *, ktime_t now);
 	enum alarmtimer_type	type;
 	int			state;

@@ -43,39 +43,12 @@ struct alarm {
 
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
-void alarm_start(struct alarm *alarm, ktime_t start);
+int alarm_start(struct alarm *alarm, ktime_t start);
 int alarm_try_to_cancel(struct alarm *alarm);
 int alarm_cancel(struct alarm *alarm);
 
 u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval);
 
-/*
- * A alarmtimer is active, when it is enqueued into timerqueue or the
- * callback function is running.
- */
-static inline int alarmtimer_active(const struct alarm *timer)
-{
-	return timer->state != ALARMTIMER_STATE_INACTIVE;
-}
-
-/*
- * Helper function to check, whether the timer is on one of the queues
- */
-static inline int alarmtimer_is_queued(struct alarm *timer)
-{
-	return timer->state & ALARMTIMER_STATE_ENQUEUED;
-}
-
-/*
- * Helper function to check, whether the timer is running the callback
- * function
- */
-static inline int alarmtimer_callback_running(struct alarm *timer)
-{
-	return timer->state & ALARMTIMER_STATE_CALLBACK;
-}
-
-
 /* Provide way to access the rtc device being used by alarmtimers */
 struct rtc_device *alarmtimer_get_rtcdev(void);
 

include/linux/clocksource.h +0 -16

index fbe89e1..4dceaf8 100644
@@ -319,22 +319,6 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz)
 	__clocksource_updatefreq_scale(cs, 1000, khz);
 }
 
-#ifdef CONFIG_GENERIC_TIME_VSYSCALL
-extern void
-update_vsyscall(struct timespec *ts, struct timespec *wtm,
-			struct clocksource *c, u32 mult);
-extern void update_vsyscall_tz(void);
-#else
-static inline void
-update_vsyscall(struct timespec *ts, struct timespec *wtm,
-			struct clocksource *c, u32 mult)
-{
-}
-
-static inline void update_vsyscall_tz(void)
-{
-}
-#endif
 
 extern void timekeeping_notify(struct clocksource *clock);
 

include/linux/jiffies.h +3 -17

index 8268054..c6d5b2a 100644
@@ -51,31 +51,17 @@
 #define SH_DIV(NOM,DEN,LSH) (   (((NOM) / (DEN)) << (LSH))              \
                              + ((((NOM) % (DEN)) << (LSH)) + (DEN) / 2) / (DEN))
 
-#ifdef CLOCK_TICK_RATE
 /* LATCH is used in the interval timer and ftape setup. */
-# define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ)	/* For divider */
+#define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ)	/* For divider */
 
-/*
- * HZ is the requested value. However the CLOCK_TICK_RATE may not allow
- * for exactly HZ. So SHIFTED_HZ is high res HZ ("<< 8" is for accuracy)
- */
-# define SHIFTED_HZ (SH_DIV(CLOCK_TICK_RATE, LATCH, 8))
-#else
-# define SHIFTED_HZ (HZ << 8)
-#endif
+extern int register_refined_jiffies(long clock_tick_rate);
 
 /* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */
-#define TICK_NSEC (SH_DIV(1000000UL * 1000, SHIFTED_HZ, 8))
+#define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ)
 
 /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
 #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
 
-/*
- * TICK_USEC_TO_NSEC is the time between ticks in nsec assuming SHIFTED_HZ and
- * a value TUSEC for TICK_USEC (can be set bij adjtimex)
- */
-#define TICK_USEC_TO_NSEC(TUSEC) (SH_DIV(TUSEC * USER_HZ * 1000, SHIFTED_HZ, 8))
-
 /* some arch's have a small-data section that can be accessed register-relative
  * but that can only take up to, say, 4-byte variables. jiffies being part of
  * an 8-byte variable may not be correctly accessed unless we force the issue

include/linux/timekeeper_internal.h new file +108 -0

new file mode 100644
index 0000000..e1d558e
@@ -0,0 +1,108 @@
+/*
+ * You SHOULD NOT be including this unless you're vsyscall
+ * handling code or timekeeping internal code!
+ */
+
+#ifndef _LINUX_TIMEKEEPER_INTERNAL_H
+#define _LINUX_TIMEKEEPER_INTERNAL_H
+
+#include <linux/clocksource.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+
+/* Structure holding internal timekeeping values. */
+struct timekeeper {
+	/* Current clocksource used for timekeeping. */
+	struct clocksource	*clock;
+	/* NTP adjusted clock multiplier */
+	u32			mult;
+	/* The shift value of the current clocksource. */
+	u32			shift;
+	/* Number of clock cycles in one NTP interval. */
+	cycle_t			cycle_interval;
+	/* Number of clock shifted nano seconds in one NTP interval. */
+	u64			xtime_interval;
+	/* shifted nano seconds left over when rounding cycle_interval */
+	s64			xtime_remainder;
+	/* Raw nano seconds accumulated per NTP interval. */
+	u32			raw_interval;
+
+	/* Current CLOCK_REALTIME time in seconds */
+	u64			xtime_sec;
+	/* Clock shifted nano seconds */
+	u64			xtime_nsec;
+
+	/* Difference between accumulated time and NTP time in ntp
+	 * shifted nano seconds. */
+	s64			ntp_error;
+	/* Shift conversion between clock shifted nano seconds and
+	 * ntp shifted nano seconds. */
+	u32			ntp_error_shift;
+
+	/*
+	 * wall_to_monotonic is what we need to add to xtime (or xtime corrected
+	 * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
+	 * at zero at system boot time, so wall_to_monotonic will be negative,
+	 * however, we will ALWAYS keep the tv_nsec part positive so we can use
+	 * the usual normalization.
+	 *
+	 * wall_to_monotonic is moved after resume from suspend for the
+	 * monotonic time not to jump. We need to add total_sleep_time to
+	 * wall_to_monotonic to get the real boot based time offset.
+	 *
+	 * - wall_to_monotonic is no longer the boot time, getboottime must be
+	 * used instead.
+	 */
+	struct timespec		wall_to_monotonic;
+	/* Offset clock monotonic -> clock realtime */
+	ktime_t			offs_real;
+	/* time spent in suspend */
+	struct timespec		total_sleep_time;
+	/* Offset clock monotonic -> clock boottime */
+	ktime_t			offs_boot;
+	/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
+	struct timespec		raw_time;
+	/* Seqlock for all timekeeper values */
+	seqlock_t		lock;
+};
+
+static inline struct timespec tk_xtime(struct timekeeper *tk)
+{
+	struct timespec ts;
+
+	ts.tv_sec = tk->xtime_sec;
+	ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
+	return ts;
+}
+
+
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
+
+extern void update_vsyscall(struct timekeeper *tk);
+extern void update_vsyscall_tz(void);
+
+#elif defined(CONFIG_GENERIC_TIME_VSYSCALL_OLD)
+
+extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm,
+				struct clocksource *c, u32 mult);
+extern void update_vsyscall_tz(void);
+
+static inline void update_vsyscall(struct timekeeper *tk)
+{
+	struct timespec xt;
+
+	xt = tk_xtime(tk);
+	update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult);
+}
+
+#else
+
+static inline void update_vsyscall(struct timekeeper *tk)
+{
+}
+static inline void update_vsyscall_tz(void)
+{
+}
+#endif
+
+#endif /* _LINUX_TIMEKEEPER_INTERNAL_H */

include/linux/timer.h +65 -100

index 6abd913..8c5a197 100644
@@ -49,147 +49,112 @@ extern struct tvec_base boot_tvec_bases;
 #endif
 
 /*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
+ * Note that all tvec_bases are at least 4 byte aligned and lower two bits
+ * of base in timer_list is guaranteed to be zero. Use them for flags.
  *
  * A deferrable timer will work normally when the system is busy, but
  * will not cause a CPU to come out of idle just to service it; instead,
  * the timer will be serviced when the CPU eventually wakes up with a
  * subsequent non-deferrable timer.
+ *
+ * An irqsafe timer is executed with IRQ disabled and it's safe to wait for
+ * the completion of the running instance from IRQ handlers, for example,
+ * by calling del_timer_sync().
+ *
+ * Note: The irq disabled callback execution is a special case for
+ * workqueue locking issues. It's not meant for executing random crap
+ * with interrupts disabled. Abuse is monitored!
  */
-#define TBASE_DEFERRABLE_FLAG		(0x1)
+#define TIMER_DEFERRABLE		0x1LU
+#define TIMER_IRQSAFE			0x2LU
 
-#define TIMER_INITIALIZER(_function, _expires, _data) {		\
+#define TIMER_FLAG_MASK			0x3LU
+
+#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
 		.entry = { .prev = TIMER_ENTRY_STATIC },	\
 		.function = (_function),			\
 		.expires = (_expires),				\
 		.data = (_data),				\
-		.base = &boot_tvec_bases,			\
+		.base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \
 		.slack = -1,					\
 		__TIMER_LOCKDEP_MAP_INITIALIZER(		\
 			__FILE__ ":" __stringify(__LINE__))	\
 	}
 
-#define TBASE_MAKE_DEFERRED(ptr) ((struct tvec_base *)		\
-		  ((unsigned char *)(ptr) + TBASE_DEFERRABLE_FLAG))
+#define TIMER_INITIALIZER(_function, _expires, _data)		\
+	__TIMER_INITIALIZER((_function), (_expires), (_data), 0)
 
-#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) {\
-		.entry = { .prev = TIMER_ENTRY_STATIC },	\
-		.function = (_function),			\
-		.expires = (_expires),				\
-		.data = (_data),				\
-		.base = TBASE_MAKE_DEFERRED(&boot_tvec_bases),	\
-		__TIMER_LOCKDEP_MAP_INITIALIZER(		\
-			__FILE__ ":" __stringify(__LINE__))	\
-	}
+#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data)	\
+	__TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE)
 
 #define DEFINE_TIMER(_name, _function, _expires, _data)		\
 	struct timer_list _name =				\
 		TIMER_INITIALIZER(_function, _expires, _data)
 
-void init_timer_key(struct timer_list *timer,
-		    const char *name,
-		    struct lock_class_key *key);
-void init_timer_deferrable_key(struct timer_list *timer,
-			       const char *name,
-			       struct lock_class_key *key);
+void init_timer_key(struct timer_list *timer, unsigned int flags,
+		    const char *name, struct lock_class_key *key);
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+extern void init_timer_on_stack_key(struct timer_list *timer,
+				    unsigned int flags, const char *name,
+				    struct lock_class_key *key);
+extern void destroy_timer_on_stack(struct timer_list *timer);
+#else
+static inline void destroy_timer_on_stack(struct timer_list *timer) { }
+static inline void init_timer_on_stack_key(struct timer_list *timer,
+					   unsigned int flags, const char *name,
+					   struct lock_class_key *key)
+{
+	init_timer_key(timer, flags, name, key);
+}
+#endif
 
 #ifdef CONFIG_LOCKDEP
-#define init_timer(timer)						\
+#define __init_timer(_timer, _flags)					\
 	do {								\
 		static struct lock_class_key __key;			\
-		init_timer_key((timer), #timer, &__key);		\
+		init_timer_key((_timer), (_flags), #_timer, &__key);	\
 	} while (0)
 
-#define init_timer_deferrable(timer)					\
+#define __init_timer_on_stack(_timer, _flags)				\
 	do {								\
 		static struct lock_class_key __key;			\
-		init_timer_deferrable_key((timer), #timer, &__key);	\
+		init_timer_on_stack_key((_timer), (_flags), #_timer, &__key); \
 	} while (0)
+#else
+#define __init_timer(_timer, _flags)					\
+	init_timer_key((_timer), (_flags), NULL, NULL)
+#define __init_timer_on_stack(_timer, _flags)				\
+	init_timer_on_stack_key((_timer), (_flags), NULL, NULL)
+#endif
 
+#define init_timer(timer)						\
+	__init_timer((timer), 0)
+#define init_timer_deferrable(timer)					\
+	__init_timer((timer), TIMER_DEFERRABLE)
 #define init_timer_on_stack(timer)					\
+	__init_timer_on_stack((timer), 0)
+
+#define __setup_timer(_timer, _fn, _data, _flags)			\
 	do {								\
-		static struct lock_class_key __key;			\
-		init_timer_on_stack_key((timer), #timer, &__key);	\
+		__init_timer((_timer), (_flags));			\
+		(_timer)->function = (_fn);				\
+		(_timer)->data = (_data);				\
 	} while (0)
 
-#define setup_timer(timer, fn, data)					\
+#define __setup_timer_on_stack(_timer, _fn, _data, _flags)		\
 	do {								\
-		static struct lock_class_key __key;			\
-		setup_timer_key((timer), #timer, &__key, (fn), (data));\
+		__init_timer_on_stack((_timer), (_flags));		\
+		(_timer)->function = (_fn);				\
+		(_timer)->data = (_data);				\
 	} while (0)
 
+#define setup_timer(timer, fn, data)					\
+	__setup_timer((timer), (fn), (data), 0)
 #define setup_timer_on_stack(timer, fn, data)				\
-	do {								\
-		static struct lock_class_key __key;			\
-		setup_timer_on_stack_key((timer), #timer, &__key,	\
-					 (fn), (data));			\
-	} while (0)
+	__setup_timer_on_stack((timer), (fn), (data), 0)
 #define setup_deferrable_timer_on_stack(timer, fn, data)		\
-	do {								\
-		static struct lock_class_key __key;			\
-		setup_deferrable_timer_on_stack_key((timer), #timer,	\
-						    &__key, (fn),	\
-						    (data));		\
-	} while (0)
-#else
-#define init_timer(timer)\
-	init_timer_key((timer), NULL, NULL)
-#define init_timer_deferrable(timer)\
-	init_timer_deferrable_key((timer), NULL, NULL)
-#define init_timer_on_stack(timer)\
-	init_timer_on_stack_key((timer), NULL, NULL)
-#define setup_timer(timer, fn, data)\
-	setup_timer_key((timer), NULL, NULL, (fn), (data))
-#define setup_timer_on_stack(timer, fn, data)\
-	setup_timer_on_stack_key((timer), NULL, NULL, (fn), (data))
-#define setup_deferrable_timer_on_stack(timer, fn, data)\
-	setup_deferrable_timer_on_stack_key((timer), NULL, NULL, (fn), (data))
-#endif
-
-#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
-extern void init_timer_on_stack_key(struct timer_list *timer,
-				    const char *name,
-				    struct lock_class_key *key);
-extern void destroy_timer_on_stack(struct timer_list *timer);
-#else
-static inline void destroy_timer_on_stack(struct timer_list *timer) { }
-static inline void init_timer_on_stack_key(struct timer_list *timer,
-					   const char *name,
-					   struct lock_class_key *key)
-{
-	init_timer_key(timer, name, key);
-}
-#endif
-
-static inline void setup_timer_key(struct timer_list * timer,
-				const char *name,
-				struct lock_class_key *key,
-				void (*function)(unsigned long),
-				unsigned long data)
-{
-	timer->function = function;
-	timer->data = data;
-	init_timer_key(timer, name, key);
-}
-
-static inline void setup_timer_on_stack_key(struct timer_list *timer,
-					const char *name,
-					struct lock_class_key *key,
-					void (*function)(unsigned long),
-					unsigned long data)
-{
-	timer->function = function;
-	timer->data = data;
-	init_timer_on_stack_key(timer, name, key);
-}
-
-extern void setup_deferrable_timer_on_stack_key(struct timer_list *timer,
-						const char *name,
-						struct lock_class_key *key,
-						void (*function)(unsigned long),
-						unsigned long data);
+	__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE)
 
 /**
  * timer_pending - is a timer pending?

kernel/time.c +1 -1

index ba744cf..d226c6a 100644
@@ -30,7 +30,7 @@
 #include <linux/export.h>
 #include <linux/timex.h>
 #include <linux/capability.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/errno.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>

kernel/time/Kconfig +4 -0

index fd42bd4..8601f0d 100644
@@ -16,6 +16,10 @@ config ARCH_CLOCKSOURCE_DATA
 config GENERIC_TIME_VSYSCALL
 	bool
 
+# Timekeeping vsyscall support
+config GENERIC_TIME_VSYSCALL_OLD
+	bool
+
 # ktime_t scalar 64bit nsec representation
 config KTIME_SCALAR
 	bool

kernel/time/alarmtimer.c +43 -75

index aa27d39..f11d83b 100644
@@ -37,7 +37,6 @@
 static struct alarm_base {
 	spinlock_t		lock;
 	struct timerqueue_head	timerqueue;
-	struct hrtimer		timer;
 	ktime_t			(*gettime)(void);
 	clockid_t		base_clockid;
 } alarm_bases[ALARM_NUMTYPE];

@@ -46,6 +45,8 @@ static struct alarm_base {
 static ktime_t freezer_delta;
 static DEFINE_SPINLOCK(freezer_delta_lock);
 
+static struct wakeup_source *ws;
+
 #ifdef CONFIG_RTC_CLASS
 /* rtc timer and device for setting alarm wakeups at suspend */
 static struct rtc_timer		rtctimer;

@@ -130,50 +131,35 @@ static inline void alarmtimer_rtc_timer_init(void) { }
  * @base: pointer to the base where the timer is being run
  * @alarm: pointer to alarm being enqueued.
  *
- * Adds alarm to a alarm_base timerqueue and if necessary sets
- * an hrtimer to run.
+ * Adds alarm to a alarm_base timerqueue
  *
  * Must hold base->lock when calling.
  */
 static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm)
 {
+	if (alarm->state & ALARMTIMER_STATE_ENQUEUED)
+		timerqueue_del(&base->timerqueue, &alarm->node);
+
 	timerqueue_add(&base->timerqueue, &alarm->node);
 	alarm->state |= ALARMTIMER_STATE_ENQUEUED;
-
-	if (&alarm->node == timerqueue_getnext(&base->timerqueue)) {
-		hrtimer_try_to_cancel(&base->timer);
-		hrtimer_start(&base->timer, alarm->node.expires,
-				HRTIMER_MODE_ABS);
-	}
 }
 
 /**
- * alarmtimer_remove - Removes an alarm timer from an alarm_base timerqueue
+ * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue
  * @base: pointer to the base where the timer is running
  * @alarm: pointer to alarm being removed
  *
- * Removes alarm to a alarm_base timerqueue and if necessary sets
- * a new timer to run.
+ * Removes alarm to a alarm_base timerqueue
  *
  * Must hold base->lock when calling.
  */
-static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm)
+static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm)
 {
-	struct timerqueue_node *next = timerqueue_getnext(&base->timerqueue);
-
 	if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED))
 		return;
 
 	timerqueue_del(&base->timerqueue, &alarm->node);
 	alarm->state &= ~ALARMTIMER_STATE_ENQUEUED;
-
-	if (next == &alarm->node) {
-		hrtimer_try_to_cancel(&base->timer);
-		next = timerqueue_getnext(&base->timerqueue);
-		if (!next)
-			return;
-		hrtimer_start(&base->timer, next->expires, HRTIMER_MODE_ABS);
-	}
 }
 
 

@@ -188,42 +174,23 @@ static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm)
  */
 static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 {
-	struct alarm_base *base = container_of(timer, struct alarm_base, timer);
-	struct timerqueue_node *next;
+	struct alarm *alarm = container_of(timer, struct alarm, timer);
+	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
-	ktime_t now;
 	int ret = HRTIMER_NORESTART;
 	int restart = ALARMTIMER_NORESTART;
 
 	spin_lock_irqsave(&base->lock, flags);
-	now = base->gettime();
-	while ((next = timerqueue_getnext(&base->timerqueue))) {
-		struct alarm *alarm;
-		ktime_t expired = next->expires;
-
-		if (expired.tv64 > now.tv64)
-			break;
-
-		alarm = container_of(next, struct alarm, node);
-
-		timerqueue_del(&base->timerqueue, &alarm->node);
-		alarm->state &= ~ALARMTIMER_STATE_ENQUEUED;
-
-		alarm->state |= ALARMTIMER_STATE_CALLBACK;
-		spin_unlock_irqrestore(&base->lock, flags);
-		if (alarm->function)
-			restart = alarm->function(alarm, now);
-		spin_lock_irqsave(&base->lock, flags);
-		alarm->state &= ~ALARMTIMER_STATE_CALLBACK;
+	alarmtimer_dequeue(base, alarm);
+	spin_unlock_irqrestore(&base->lock, flags);
 
-		if (restart != ALARMTIMER_NORESTART) {
-			timerqueue_add(&base->timerqueue, &alarm->node);
-			alarm->state |= ALARMTIMER_STATE_ENQUEUED;
-		}
-	}
+	if (alarm->function)
+		restart = alarm->function(alarm, base->gettime());
 
-	if (next) {
-		hrtimer_set_expires(&base->timer, next->expires);
+	spin_lock_irqsave(&base->lock, flags);
+	if (restart != ALARMTIMER_NORESTART) {
+		hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+		alarmtimer_enqueue(base, alarm);
 		ret = HRTIMER_RESTART;
 	}
 	spin_unlock_irqrestore(&base->lock, flags);

@@ -250,6 +217,7 @@ static int alarmtimer_suspend(struct device *dev)
 	unsigned long flags;
 	struct rtc_device *rtc;
 	int i;
+	int ret;
 
 	spin_lock_irqsave(&freezer_delta_lock, flags);
 	min = freezer_delta;

@@ -279,8 +247,10 @@ static int alarmtimer_suspend(struct device *dev)
 	if (min.tv64 == 0)
 		return 0;
 
-	/* XXX - Should we enforce a minimum sleep time? */
-	WARN_ON(min.tv64 < NSEC_PER_SEC);
+	if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) {
+		__pm_wakeup_event(ws, 2 * MSEC_PER_SEC);
+		return -EBUSY;
+	}
 
 	/* Setup an rtc timer to fire that far in the future */
 	rtc_timer_cancel(rtc, &rtctimer);

@@ -288,9 +258,11 @@ static int alarmtimer_suspend(struct device *dev)
 	now = rtc_tm_to_ktime(tm);
 	now = ktime_add(now, min);
 
-	rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0));
-
-	return 0;
+	/* Set alarm, if in the past reject suspend briefly to handle */
+	ret = rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0));
+	if (ret < 0)
+		__pm_wakeup_event(ws, MSEC_PER_SEC);
+	return ret;
 }
 #else
 static int alarmtimer_suspend(struct device *dev)

@@ -324,6 +296,9 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		enum alarmtimer_restart (*function)(struct alarm *, ktime_t))
 {
 	timerqueue_init(&alarm->node);
+	hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid,
+			HRTIMER_MODE_ABS);
+	alarm->timer.function = alarmtimer_fired;
 	alarm->function = function;
 	alarm->type = type;
 	alarm->state = ALARMTIMER_STATE_INACTIVE;

@@ -334,17 +309,19 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
-void alarm_start(struct alarm *alarm, ktime_t start)
+int alarm_start(struct alarm *alarm, ktime_t start)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&base->lock, flags);
-	if (alarmtimer_active(alarm))
-		alarmtimer_remove(base, alarm);
 	alarm->node.expires = start;
 	alarmtimer_enqueue(base, alarm);
+	ret = hrtimer_start(&alarm->timer, alarm->node.expires,
+				HRTIMER_MODE_ABS);
 	spin_unlock_irqrestore(&base->lock, flags);
+	return ret;
 }
 
 /**

@@ -358,18 +335,12 @@ int alarm_try_to_cancel(struct alarm *alarm)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
 	unsigned long flags;
-	int ret = -1;
-	spin_lock_irqsave(&base->lock, flags);
-
-	if (alarmtimer_callback_running(alarm))
-		goto out;
+	int ret;
 
-	if (alarmtimer_is_queued(alarm)) {
-		alarmtimer_remove(base, alarm);
-		ret = 1;
-	} else
-		ret = 0;
-out:
+	spin_lock_irqsave(&base->lock, flags);
+	ret = hrtimer_try_to_cancel(&alarm->timer);
+	if (ret >= 0)
+		alarmtimer_dequeue(base, alarm);
 	spin_unlock_irqrestore(&base->lock, flags);
 	return ret;
 }

@@ -802,10 +773,6 @@ static int __init alarmtimer_init(void)
 	for (i = 0; i < ALARM_NUMTYPE; i++) {
 		timerqueue_init_head(&alarm_bases[i].timerqueue);
 		spin_lock_init(&alarm_bases[i].lock);
-		hrtimer_init(&alarm_bases[i].timer,
-				alarm_bases[i].base_clockid,
-				HRTIMER_MODE_ABS);
-		alarm_bases[i].timer.function = alarmtimer_fired;
 	}
 
 	error = alarmtimer_rtc_interface_setup();

@@ -821,6 +788,7 @@ static int __init alarmtimer_init(void)
 		error = PTR_ERR(pdev);
 		goto out_drv;
 	}
+	ws = wakeup_source_register("alarmtimer");
 	return 0;
 
 out_drv:

kernel/time/jiffies.c +31 -1

index 46da053..6629bf7 100644
@@ -37,7 +37,7 @@
  * requested HZ value. It is also not recommended
  * for "tick-less" systems.
  */
-#define NSEC_PER_JIFFY	((u32)((((u64)NSEC_PER_SEC)<<8)/SHIFTED_HZ))
+#define NSEC_PER_JIFFY	((NSEC_PER_SEC+HZ/2)/HZ)
 
 /* Since jiffies uses a simple NSEC_PER_JIFFY multiplier
  * conversion, the .shift value could be zero. However

@@ -95,3 +95,33 @@ struct clocksource * __init __weak clocksource_default_clock(void)
 {
 	return &clocksource_jiffies;
 }
+
+struct clocksource refined_jiffies;
+
+int register_refined_jiffies(long cycles_per_second)
+{
+	u64 nsec_per_tick, shift_hz;
+	long cycles_per_tick;
+
+
+
+	refined_jiffies = clocksource_jiffies;
+	refined_jiffies.name = "refined-jiffies";
+	refined_jiffies.rating++;
+
+	/* Calc cycles per tick */
+	cycles_per_tick = (cycles_per_second + HZ/2)/HZ;
+	/* shift_hz stores hz<<8 for extra accuracy */
+	shift_hz = (u64)cycles_per_second << 8;
+	shift_hz += cycles_per_tick/2;
+	do_div(shift_hz, cycles_per_tick);
+	/* Calculate nsec_per_tick using shift_hz */
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
+	nsec_per_tick += (u32)shift_hz/2;
+	do_div(nsec_per_tick, (u32)shift_hz);
+
+	refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT;
+
+	clocksource_register(&refined_jiffies);
+	return 0;
+}

kernel/time/timekeeping.c +34 -83

index d3b91e7..3eb3fc7c 100644
@@ -8,6 +8,7 @@
  *
  */
 
+#include <linux/timekeeper_internal.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>

@@ -21,61 +22,6 @@
 #include <linux/tick.h>
 #include <linux/stop_machine.h>
 
-/* Structure holding internal timekeeping values. */
-struct timekeeper {
-	/* Current clocksource used for timekeeping. */
-	struct clocksource	*clock;
-	/* NTP adjusted clock multiplier */
-	u32			mult;
-	/* The shift value of the current clocksource. */
-	u32			shift;
-	/* Number of clock cycles in one NTP interval. */
-	cycle_t			cycle_interval;
-	/* Number of clock shifted nano seconds in one NTP interval. */
-	u64			xtime_interval;
-	/* shifted nano seconds left over when rounding cycle_interval */
-	s64			xtime_remainder;
-	/* Raw nano seconds accumulated per NTP interval. */
-	u32			raw_interval;
-
-	/* Current CLOCK_REALTIME time in seconds */
-	u64			xtime_sec;
-	/* Clock shifted nano seconds */
-	u64			xtime_nsec;
-
-	/* Difference between accumulated time and NTP time in ntp
-	 * shifted nano seconds. */
-	s64			ntp_error;
-	/* Shift conversion between clock shifted nano seconds and
-	 * ntp shifted nano seconds. */
-	u32			ntp_error_shift;
-
-	/*
-	 * wall_to_monotonic is what we need to add to xtime (or xtime corrected
-	 * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
-	 * at zero at system boot time, so wall_to_monotonic will be negative,
-	 * however, we will ALWAYS keep the tv_nsec part positive so we can use
-	 * the usual normalization.
-	 *
-	 * wall_to_monotonic is moved after resume from suspend for the
-	 * monotonic time not to jump. We need to add total_sleep_time to
-	 * wall_to_monotonic to get the real boot based time offset.
-	 *
-	 * - wall_to_monotonic is no longer the boot time, getboottime must be
-	 * used instead.
-	 */
-	struct timespec		wall_to_monotonic;
-	/* Offset clock monotonic -> clock realtime */
-	ktime_t			offs_real;
-	/* time spent in suspend */
-	struct timespec		total_sleep_time;
-	/* Offset clock monotonic -> clock boottime */
-	ktime_t			offs_boot;
-	/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
-	struct timespec		raw_time;
-	/* Seqlock for all timekeeper values */
-	seqlock_t		lock;
-};
 
 static struct timekeeper timekeeper;
 

@@ -96,15 +42,6 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
 	}
 }
 
-static struct timespec tk_xtime(struct timekeeper *tk)
-{
-	struct timespec ts;
-
-	ts.tv_sec = tk->xtime_sec;
-	ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
-	return ts;
-}
-
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts)
 {
 	tk->xtime_sec = ts->tv_sec;

@@ -246,14 +183,11 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
 /* must hold write on timekeeper.lock */
 static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
-	struct timespec xt;
-
 	if (clearntp) {
 		tk->ntp_error = 0;
 		ntp_clear();
 	}
-	xt = tk_xtime(tk);
-	update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult);
+	update_vsyscall(tk);
 }
 
 /**

@@ -1111,7 +1045,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
-	raw_nsecs = tk->raw_interval << shift;
+	raw_nsecs = (u64)tk->raw_interval << shift;
 	raw_nsecs += tk->raw_time.tv_nsec;
 	if (raw_nsecs >= NSEC_PER_SEC) {
 		u64 raw_secs = raw_nsecs;

@@ -1128,6 +1062,33 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	return offset;
 }
 
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
+static inline void old_vsyscall_fixup(struct timekeeper *tk)
+{
+	s64 remainder;
+
+	/*
+	* Store only full nanoseconds into xtime_nsec after rounding
+	* it up and add the remainder to the error difference.
+	* XXX - This is necessary to avoid small 1ns inconsistnecies caused
+	* by truncating the remainder in vsyscalls. However, it causes
+	* additional work to be done in timekeeping_adjust(). Once
+	* the vsyscall implementations are converted to use xtime_nsec
+	* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
+	* users are removed, this can be killed.
+	*/
+	remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
+	tk->xtime_nsec -= remainder;
+	tk->xtime_nsec += 1ULL << tk->shift;
+	tk->ntp_error += remainder << tk->ntp_error_shift;
+
+}
+#else
+#define old_vsyscall_fixup(tk)
+#endif
+
+
+
 /**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *

@@ -1139,7 +1100,6 @@ static void update_wall_time(void)
 	cycle_t offset;
 	int shift = 0, maxshift;
 	unsigned long flags;
-	s64 remainder;
 
 	write_seqlock_irqsave(&tk->lock, flags);
 

@@ -1181,20 +1141,11 @@ static void update_wall_time(void)
 	/* correct the clock when NTP error is too big */
 	timekeeping_adjust(tk, offset);
 
-
 	/*
-	* Store only full nanoseconds into xtime_nsec after rounding
-	* it up and add the remainder to the error difference.
-	* XXX - This is necessary to avoid small 1ns inconsistnecies caused
-	* by truncating the remainder in vsyscalls. However, it causes
-	* additional work to be done in timekeeping_adjust(). Once
-	* the vsyscall implementations are converted to use xtime_nsec
-	* (shifted nanoseconds), this can be killed.
-	*/
-	remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
-	tk->xtime_nsec -= remainder;
-	tk->xtime_nsec += 1ULL << tk->shift;
-	tk->ntp_error += remainder << tk->ntp_error_shift;
+	 * XXX This can be killed once everyone converts
+	 * to the new update_vsyscall.
+	 */
+	old_vsyscall_fixup(tk);
 
 	/*
 	 * Finally, make sure that after the rounding

kernel/timer.c +55 -63

index 8c5e7b9..367d008 100644
@@ -63,6 +63,7 @@ EXPORT_SYMBOL(jiffies_64);
 #define TVR_SIZE (1 << TVR_BITS)
 #define TVN_MASK (TVN_SIZE - 1)
 #define TVR_MASK (TVR_SIZE - 1)
+#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
 
 struct tvec {
 	struct list_head vec[TVN_SIZE];

@@ -92,24 +93,25 @@ static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 /* Functions below help us manage 'deferrable' flag */
 static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
 {
-	return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
+	return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE);
 }
 
-static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+static inline unsigned int tbase_get_irqsafe(struct tvec_base *base)
 {
-	return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
+	return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE);
 }
 
-static inline void timer_set_deferrable(struct timer_list *timer)
+static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
 {
-	timer->base = TBASE_MAKE_DEFERRED(timer->base);
+	return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK));
 }
 
 static inline void
 timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
 {
-	timer->base = (struct tvec_base *)((unsigned long)(new_base) |
-				      tbase_get_deferrable(timer->base));
+	unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK;
+
+	timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags);
 }
 
 static unsigned long round_jiffies_common(unsigned long j, int cpu,

@@ -358,11 +360,12 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer)
 		vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
 	} else {
 		int i;
-		/* If the timeout is larger than 0xffffffff on 64-bit
-		 * architectures then we use the maximum timeout:
+		/* If the timeout is larger than MAX_TVAL (on 64-bit
+		 * architectures or with CONFIG_BASE_SMALL=1) then we
+		 * use the maximum timeout.
 		 */
-		if (idx > 0xffffffffUL) {
-			idx = 0xffffffffUL;
+		if (idx > MAX_TVAL) {
+			idx = MAX_TVAL;
 			expires = idx + base->timer_jiffies;
 		}
 		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;

@@ -563,16 +566,14 @@ static inline void debug_timer_assert_init(struct timer_list *timer)
 	debug_object_assert_init(timer, &timer_debug_descr);
 }
 
-static void __init_timer(struct timer_list *timer,
-			 const char *name,
-			 struct lock_class_key *key);
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+			  const char *name, struct lock_class_key *key);
 
-void init_timer_on_stack_key(struct timer_list *timer,
-			     const char *name,
-			     struct lock_class_key *key)
+void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags,
+			     const char *name, struct lock_class_key *key)
 {
 	debug_object_init_on_stack(timer, &timer_debug_descr);
-	__init_timer(timer, name, key);
+	do_init_timer(timer, flags, name, key);
 }
 EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
 

@@ -613,12 +614,13 @@ static inline void debug_assert_init(struct timer_list *timer)
 	debug_timer_assert_init(timer);
 }
 
-static void __init_timer(struct timer_list *timer,
-			 const char *name,
-			 struct lock_class_key *key)
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+			  const char *name, struct lock_class_key *key)
 {
+	struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+
 	timer->entry.next = NULL;
-	timer->base = __raw_get_cpu_var(tvec_bases);
+	timer->base = (void *)((unsigned long)base | flags);
 	timer->slack = -1;
 #ifdef CONFIG_TIMER_STATS
 	timer->start_site = NULL;

@@ -628,22 +630,10 @@ static void __init_timer(struct timer_list *timer,
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
 
-void setup_deferrable_timer_on_stack_key(struct timer_list *timer,
-					 const char *name,
-					 struct lock_class_key *key,
-					 void (*function)(unsigned long),
-					 unsigned long data)
-{
-	timer->function = function;
-	timer->data = data;
-	init_timer_on_stack_key(timer, name, key);
-	timer_set_deferrable(timer);
-}
-EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key);
-
 /**
  * init_timer_key - initialize a timer
  * @timer: the timer to be initialized
+ * @flags: timer flags
  * @name: name of the timer
  * @key: lockdep class key of the fake lock used for tracking timer
  *       sync lock dependencies

@@ -651,24 +641,14 @@ EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key);
  * init_timer_key() must be done to a timer prior calling *any* of the
  * other timer functions.
  */
-void init_timer_key(struct timer_list *timer,
-		    const char *name,
-		    struct lock_class_key *key)
+void init_timer_key(struct timer_list *timer, unsigned int flags,
+		    const char *name, struct lock_class_key *key)
 {
 	debug_init(timer);
-	__init_timer(timer, name, key);
+	do_init_timer(timer, flags, name, key);
 }
 EXPORT_SYMBOL(init_timer_key);
 
-void init_timer_deferrable_key(struct timer_list *timer,
-			       const char *name,
-			       struct lock_class_key *key)
-{
-	init_timer_key(timer, name, key);
-	timer_set_deferrable(timer);
-}
-EXPORT_SYMBOL(init_timer_deferrable_key);
-
 static inline void detach_timer(struct timer_list *timer, bool clear_pending)
 {
 	struct list_head *entry = &timer->entry;

@@ -686,7 +666,7 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
 {
 	detach_timer(timer, true);
 	if (!tbase_get_deferrable(timer->base))
-		timer->base->active_timers--;
+		base->active_timers--;
 }
 
 static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,

@@ -697,7 +677,7 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
 
 	detach_timer(timer, clear_pending);
 	if (!tbase_get_deferrable(timer->base)) {
-		timer->base->active_timers--;
+		base->active_timers--;
 		if (timer->expires == base->next_timer)
 			base->next_timer = base->timer_jiffies;
 	}

@@ -1029,14 +1009,14 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
- * completion of the timer's handler. The timer's handler must not call
- * add_timer_on(). Upon exit the timer is not queued and the handler is
- * not running on any CPU.
+ * interrupt contexts unless the timer is an irqsafe one. The caller must
+ * not hold locks which would prevent completion of the timer's
+ * handler. The timer's handler must not call add_timer_on(). Upon exit the
+ * timer is not queued and the handler is not running on any CPU.
  *
- * Note: You must not hold locks that are held in interrupt context
- *   while calling this function. Even if the lock has nothing to do
- *   with the timer in question.  Here's why:
+ * Note: For !irqsafe timers, you must not hold locks that are held in
+ *   interrupt context while calling this function. Even if the lock has
+ *   nothing to do with the timer in question.  Here's why:
  *
  *    CPU0                             CPU1
  *    ----                             ----

@@ -1073,7 +1053,7 @@ int del_timer_sync(struct timer_list *timer)
 	 * don't use it in hardirq context, because it
 	 * could lead to deadlock.
 	 */
-	WARN_ON(in_irq());
+	WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base));
 	for (;;) {
 		int ret = try_to_del_timer_sync(timer);
 		if (ret >= 0)

@@ -1180,19 +1160,27 @@ static inline void __run_timers(struct tvec_base *base)
 		while (!list_empty(head)) {
 			void (*fn)(unsigned long);
 			unsigned long data;
+			bool irqsafe;
 
 			timer = list_first_entry(head, struct timer_list,entry);
 			fn = timer->function;
 			data = timer->data;
+			irqsafe = tbase_get_irqsafe(timer->base);
 
 			timer_stats_account_timer(timer);
 
 			base->running_timer = timer;
 			detach_expired_timer(timer, base);
 
-			spin_unlock_irq(&base->lock);
-			call_timer_fn(timer, fn, data);
-			spin_lock_irq(&base->lock);
+			if (irqsafe) {
+				spin_unlock(&base->lock);
+				call_timer_fn(timer, fn, data);
+				spin_lock(&base->lock);
+			} else {
+				spin_unlock_irq(&base->lock);
+				call_timer_fn(timer, fn, data);
+				spin_lock_irq(&base->lock);
+			}
 		}
 	}
 	base->running_timer = NULL;

@@ -1791,9 +1779,13 @@ static struct notifier_block __cpuinitdata timers_nb = {
 
 void __init init_timers(void)
 {
-	int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
-				(void *)(long)smp_processor_id());
+	int err;
+
+	/* ensure there are enough low bits for flags in timer->base pointer */
+	BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
 
+	err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
+			       (void *)(long)smp_processor_id());
 	init_timer_stats();
 
 	BUG_ON(err != NOTIFY_OK);