Merge branch 'v28-timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'v28-timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (36 commits)
  fix documentation of sysrq-q really
  Fix documentation of sysrq-q
  timer_list: add base address to clock base
  timer_list: print cpu number of clockevents device
  timer_list: print real timer address
  NOHZ: restart tick device from irq_enter()
  NOHZ: split tick_nohz_restart_sched_tick()
  NOHZ: unify the nohz function calls in irq_enter()
  timers: fix itimer/many thread hang, fix
  timers: fix itimer/many thread hang, v3
  ntp: improve adjtimex frequency rounding
  timekeeping: fix rounding problem during clock update
  ntp: let update_persistent_clock() sleep
  hrtimer: reorder struct hrtimer to save 8 bytes on 64bit builds
  posix-timers: lock_timer: make it readable
  posix-timers: lock_timer: kill the bogus ->it_id check
  posix-timers: kill ->it_sigev_signo and ->it_sigev_value
  posix-timers: sys_timer_create: cleanup the error handling
  posix-timers: move the initialization of timer->sigq from send to create path
  posix-timers: sys_timer_create: simplify and s/tasklist/rcu/
  ...

Fix trivial conflicts due to sysrq-q description clahes in
Documentation/sysrq.txt and drivers/char/sysrq.c

include/linux/clocksource.h

@@ -45,7 +45,8 @@ struct clocksource;
  * @read:		returns a cycle value
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
- * @mult:		cycle to nanosecond multiplier
+ * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
+ * @mult_orig:		cycle to nanosecond multiplier (unadjusted by NTP)
  * @shift:		cycle to nanosecond divisor (power of two)
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
@@ -63,6 +64,7 @@ struct clocksource {
 	cycle_t (*read)(void);
 	cycle_t mask;
 	u32 mult;
+	u32 mult_orig;
 	u32 shift;
 	unsigned long flags;
 	cycle_t (*vread)(void);
@@ -77,6 +79,7 @@ struct clocksource {
 	/* timekeeping specific data, ignore */
 	cycle_t cycle_interval;
 	u64	xtime_interval;
+	u32	raw_interval;
 	/*
 	 * Second part is written at each timer interrupt
 	 * Keep it in a different cache line to dirty no
@@ -85,6 +88,7 @@ struct clocksource {
 	cycle_t cycle_last ____cacheline_aligned_in_smp;
 	u64 xtime_nsec;
 	s64 error;
+	struct timespec raw_time;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
@@ -201,17 +205,19 @@ static inline void clocksource_calculate_interval(struct clocksource *c,
 {
 	u64 tmp;
 
-	/* XXX - All of this could use a whole lot of optimization */
+	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = length_nsec;
 	tmp <<= c->shift;
-	tmp += c->mult/2;
-	do_div(tmp, c->mult);
+	tmp += c->mult_orig/2;
+	do_div(tmp, c->mult_orig);
 
 	c->cycle_interval = (cycle_t)tmp;
 	if (c->cycle_interval == 0)
 		c->cycle_interval = 1;
 
+	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
+	c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift;
 }
 
 

include/linux/hrtimer.h

@@ -125,12 +125,12 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
-	enum hrtimer_cb_mode		cb_mode;
 	struct list_head		cb_entry;
+	enum hrtimer_cb_mode		cb_mode;
 #ifdef CONFIG_TIMER_STATS
+	int				start_pid;
 	void				*start_site;
 	char				start_comm[16];
-	int				start_pid;
 #endif
 };
 
@@ -155,10 +155,8 @@ struct hrtimer_sleeper {
  * @first:		pointer to the timer node which expires first
  * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
- * @get_softirq_time:	function to retrieve the current time from the softirq
  * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
- * @reprogram:		function to reprogram the timer event
  */
 struct hrtimer_clock_base {
 	struct hrtimer_cpu_base	*cpu_base;
@@ -167,13 +165,9 @@ struct hrtimer_clock_base {
 	struct rb_node		*first;
 	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
-	ktime_t			(*get_softirq_time)(void);
 	ktime_t			softirq_time;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t			offset;
-	int			(*reprogram)(struct hrtimer *t,
-					     struct hrtimer_clock_base *b,
-					     ktime_t n);
 #endif
 };
 

include/linux/kernel_stat.h

@@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq)
 	return sum;
 }
 
+extern unsigned long long task_delta_exec(struct task_struct *);
 extern void account_user_time(struct task_struct *, cputime_t);
 extern void account_user_time_scaled(struct task_struct *, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t);

include/linux/posix-timers.h

@@ -45,8 +45,6 @@ struct k_itimer {
 	int it_requeue_pending;		/* waiting to requeue this timer */
 #define REQUEUE_PENDING 1
 	int it_sigev_notify;		/* notify word of sigevent struct */
-	int it_sigev_signo;		/* signo word of sigevent struct */
-	sigval_t it_sigev_value;	/* value word of sigevent struct */
 	struct task_struct *it_process;	/* process to send signal to */
 	struct sigqueue *sigq;		/* signal queue entry. */
 	union {
@@ -115,4 +113,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 
+void update_rlimit_cpu(unsigned long rlim_new);
+
 #endif

include/linux/sched.h

@@ -434,6 +434,39 @@ struct pacct_struct {
 	unsigned long		ac_minflt, ac_majflt;
 };
 
+/**
+ * struct task_cputime - collected CPU time counts
+ * @utime:		time spent in user mode, in &cputime_t units
+ * @stime:		time spent in kernel mode, in &cputime_t units
+ * @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 {
+	cputime_t utime;
+	cputime_t stime;
+	unsigned long long sum_exec_runtime;
+};
+/* Alternate field names when used to cache expirations. */
+#define prof_exp	stime
+#define virt_exp	utime
+#define sched_exp	sum_exec_runtime
+
+/**
+ * struct thread_group_cputime - thread group interval timer counts
+ * @totals:		thread group interval timers; substructure for
+ *			uniprocessor kernel, per-cpu for SMP kernel.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU clock calculations.
+ */
+struct thread_group_cputime {
+	struct task_cputime *totals;
+};
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -479,6 +512,17 @@ struct signal_struct {
 	cputime_t it_prof_expires, it_virt_expires;
 	cputime_t it_prof_incr, it_virt_incr;
 
+	/*
+	 * Thread group totals for process CPU clocks.
+	 * See thread_group_cputime(), et al, for details.
+	 */
+	struct thread_group_cputime cputime;
+
+	/* Earliest-expiration cache. */
+	struct task_cputime cputime_expires;
+
+	struct list_head cpu_timers[3];
+
 	/* job control IDs */
 
 	/*
@@ -509,7 +553,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
-	cputime_t utime, stime, cutime, cstime;
+	cputime_t cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -517,14 +561,6 @@ struct signal_struct {
 	unsigned long inblock, oublock, cinblock, coublock;
 	struct task_io_accounting ioac;
 
-	/*
-	 * Cumulative ns of scheduled CPU time for dead threads in the
-	 * group, not including a zombie group leader.  (This only differs
-	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
-	 * other than jiffies.)
-	 */
-	unsigned long long sum_sched_runtime;
-
 	/*
 	 * We don't bother to synchronize most readers of this at all,
 	 * because there is no reader checking a limit that actually needs
@@ -536,8 +572,6 @@ struct signal_struct {
 	 */
 	struct rlimit rlim[RLIM_NLIMITS];
 
-	struct list_head cpu_timers[3];
-
 	/* keep the process-shared keyrings here so that they do the right
 	 * thing in threads created with CLONE_THREAD */
 #ifdef CONFIG_KEYS
@@ -1146,8 +1180,7 @@ struct task_struct {
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
 	unsigned long min_flt, maj_flt;
 
-  	cputime_t it_prof_expires, it_virt_expires;
-	unsigned long long it_sched_expires;
+	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
 
 /* process credentials */
@@ -1597,6 +1630,7 @@ extern unsigned long long cpu_clock(int cpu);
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
+extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
@@ -2093,6 +2127,30 @@ static inline int spin_needbreak(spinlock_t *lock)
 #endif
 }
 
+/*
+ * Thread group CPU time accounting.
+ */
+
+extern int thread_group_cputime_alloc(struct task_struct *);
+extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
+
+static inline void thread_group_cputime_init(struct signal_struct *sig)
+{
+	sig->cputime.totals = NULL;
+}
+
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
+{
+	if (curr->signal->cputime.totals)
+		return 0;
+	return thread_group_cputime_alloc(curr);
+}
+
+static inline void thread_group_cputime_free(struct signal_struct *sig)
+{
+	free_percpu(sig->cputime.totals);
+}
+
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.

include/linux/tick.h

@@ -96,9 +96,11 @@ extern cpumask_t *tick_get_broadcast_oneshot_mask(void);
 extern void tick_clock_notify(void);
 extern int tick_check_oneshot_change(int allow_nohz);
 extern struct tick_sched *tick_get_tick_sched(int cpu);
+extern void tick_check_idle(int cpu);
 # else
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 # endif
 
 #else /* CONFIG_GENERIC_CLOCKEVENTS */
@@ -106,26 +108,23 @@ static inline void tick_init(void) { }
 static inline void tick_cancel_sched_timer(int cpu) { }
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 # ifdef CONFIG_NO_HZ
 extern void tick_nohz_stop_sched_tick(int inidle);
 extern void tick_nohz_restart_sched_tick(void);
-extern void tick_nohz_update_jiffies(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
-extern void tick_nohz_stop_idle(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 # else
 static inline void tick_nohz_stop_sched_tick(int inidle) { }
 static inline void tick_nohz_restart_sched_tick(void) { }
-static inline void tick_nohz_update_jiffies(void) { }
 static inline ktime_t tick_nohz_get_sleep_length(void)
 {
 	ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
 
 	return len;
 }
-static inline void tick_nohz_stop_idle(int cpu) { }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 

include/linux/time.h

@@ -119,6 +119,7 @@ extern int do_setitimer(int which, struct itimerval *value,
 extern unsigned int alarm_setitimer(unsigned int seconds);
 extern int do_getitimer(int which, struct itimerval *value);
 extern void getnstimeofday(struct timespec *tv);
+extern void getrawmonotonic(struct timespec *ts);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
 
@@ -127,6 +128,9 @@ extern int timekeeping_valid_for_hres(void);
 extern void update_wall_time(void);
 extern void update_xtime_cache(u64 nsec);
 
+struct tms;
+extern void do_sys_times(struct tms *);
+
 /**
  * timespec_to_ns - Convert timespec to nanoseconds
  * @ts:		pointer to the timespec variable to be converted
@@ -216,6 +220,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC			1
 #define CLOCK_PROCESS_CPUTIME_ID	2
 #define CLOCK_THREAD_CPUTIME_ID		3
+#define CLOCK_MONOTONIC_RAW		4
 
 /*
  * The IDs of various hardware clocks:

include/linux/timex.h

@@ -82,7 +82,7 @@
  */
 #define SHIFT_USEC 16		/* frequency offset scale (shift) */
 #define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
-#define PPM_SCALE_INV_SHIFT 20
+#define PPM_SCALE_INV_SHIFT 19
 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
 		       PPM_SCALE + 1)
 
@@ -141,8 +141,15 @@ struct timex {
 #define ADJ_MICRO		0x1000	/* select microsecond resolution */
 #define ADJ_NANO		0x2000	/* select nanosecond resolution */
 #define ADJ_TICK		0x4000	/* tick value */
+
+#ifdef __KERNEL__
+#define ADJ_ADJTIME		0x8000	/* switch between adjtime/adjtimex modes */
+#define ADJ_OFFSET_SINGLESHOT	0x0001	/* old-fashioned adjtime */
+#define ADJ_OFFSET_READONLY	0x2000	/* read-only adjtime */
+#else
 #define ADJ_OFFSET_SINGLESHOT	0x8001	/* old-fashioned adjtime */
-#define ADJ_OFFSET_SS_READ	0xa001  /* read-only adjtime */
+#define ADJ_OFFSET_SS_READ	0xa001	/* read-only adjtime */
+#endif
 
 /* xntp 3.4 compatibility names */
 #define MOD_OFFSET	ADJ_OFFSET