Merge branch 'v28-timers-for-linus' of...

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

Documentation/sysrq.txt

@@ -95,8 +95,9 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 
 'p'     - Will dump the current registers and flags to your console.
 
-'q'     - Will dump a list of all running hrtimers.
-	  WARNING: Does not cover any other timers
+'q'     - Will dump per CPU lists of all armed hrtimers (but NOT regular
+          timer_list timers) and detailed information about all
+          clockevent devices.
 
 'r'     - Turns off keyboard raw mode and sets it to XLATE.
 

drivers/char/sysrq.c

@@ -168,7 +168,7 @@ static void sysrq_handle_show_timers(int key, struct tty_struct *tty)
 static struct sysrq_key_op sysrq_show_timers_op = {
 	.handler	= sysrq_handle_show_timers,
 	.help_msg	= "show-all-timers(Q)",
-	.action_msg	= "Show pending hrtimers (no others)",
+	.action_msg	= "Show clockevent devices & pending hrtimers (no others)",
 };
 
 static void sysrq_handle_mountro(int key, struct tty_struct *tty)

drivers/clocksource/acpi_pm.c

@@ -237,9 +237,12 @@ static int __init parse_pmtmr(char *arg)
 
 	if (strict_strtoul(arg, 16, &base))
 		return -EINVAL;
-
+#ifdef CONFIG_X86_64
+	if (base > UINT_MAX)
+		return -ERANGE;
+#endif
 	printk(KERN_INFO "PMTMR IOPort override: 0x%04x -> 0x%04lx\n",
-	       (unsigned int)pmtmr_ioport, base);
+	       pmtmr_ioport, base);
 	pmtmr_ioport = base;
 
 	return 1;

fs/binfmt_elf.c

@@ -1341,20 +1341,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 	prstatus->pr_pgrp = task_pgrp_vnr(p);
 	prstatus->pr_sid = task_session_vnr(p);
 	if (thread_group_leader(p)) {
+		struct task_cputime cputime;
+
 		/*
-		 * This is the record for the group leader.  Add in the
-		 * cumulative times of previous dead threads.  This total
-		 * won't include the time of each live thread whose state
-		 * is included in the core dump.  The final total reported
-		 * to our parent process when it calls wait4 will include
-		 * those sums as well as the little bit more time it takes
-		 * this and each other thread to finish dying after the
-		 * core dump synchronization phase.
+		 * This is the record for the group leader.  It shows the
+		 * group-wide total, not its individual thread total.
 		 */
-		cputime_to_timeval(cputime_add(p->utime, p->signal->utime),
-				   &prstatus->pr_utime);
-		cputime_to_timeval(cputime_add(p->stime, p->signal->stime),
-				   &prstatus->pr_stime);
+		thread_group_cputime(p, &cputime);
+		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
+		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
 	} else {
 		cputime_to_timeval(p->utime, &prstatus->pr_utime);
 		cputime_to_timeval(p->stime, &prstatus->pr_stime);

fs/proc/array.c

@@ -388,20 +388,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 		/* add up live thread stats at the group level */
 		if (whole) {
+			struct task_cputime cputime;
 			struct task_struct *t = task;
 			do {
 				min_flt += t->min_flt;
 				maj_flt += t->maj_flt;
-				utime = cputime_add(utime, task_utime(t));
-				stime = cputime_add(stime, task_stime(t));
 				gtime = cputime_add(gtime, task_gtime(t));
 				t = next_thread(t);
 			} while (t != task);
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			utime = cputime_add(utime, sig->utime);
-			stime = cputime_add(stime, sig->stime);
+			thread_group_cputime(task, &cputime);
+			utime = cputime.utime;
+			stime = cputime.stime;
 			gtime = cputime_add(gtime, sig->gtime);
 		}
 

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 */
+#endif
 
 /* xntp 3.4 compatibility names */
 #define MOD_OFFSET	ADJ_OFFSET

kernel/compat.c

@@ -23,6 +23,7 @@
 #include <linux/timex.h>
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
+#include <linux/times.h>
 
 #include <asm/uaccess.h>
 
@@ -208,49 +209,23 @@ asmlinkage long compat_sys_setitimer(int which,
 	return 0;
 }
 
+static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
+{
+	return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
+}
+
 asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
 {
-	/*
-	 *	In the SMP world we might just be unlucky and have one of
-	 *	the times increment as we use it. Since the value is an
-	 *	atomically safe type this is just fine. Conceptually its
-	 *	as if the syscall took an instant longer to occur.
-	 */
 	if (tbuf) {
+		struct tms tms;
 		struct compat_tms tmp;
-		struct task_struct *tsk = current;
-		struct task_struct *t;
-		cputime_t utime, stime, cutime, cstime;
-
-		read_lock(&tasklist_lock);
-		utime = tsk->signal->utime;
-		stime = tsk->signal->stime;
-		t = tsk;
-		do {
-			utime = cputime_add(utime, t->utime);
-			stime = cputime_add(stime, t->stime);
-			t = next_thread(t);
-		} while (t != tsk);
 
-		/*
-		 * While we have tasklist_lock read-locked, no dying thread
-		 * can be updating current->signal->[us]time.  Instead,
-		 * we got their counts included in the live thread loop.
-		 * However, another thread can come in right now and
-		 * do a wait call that updates current->signal->c[us]time.
-		 * To make sure we always see that pair updated atomically,
-		 * we take the siglock around fetching them.
-		 */
-		spin_lock_irq(&tsk->sighand->siglock);
-		cutime = tsk->signal->cutime;
-		cstime = tsk->signal->cstime;
-		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
-
-		tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime));
-		tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime));
-		tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime));
-		tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime));
+		do_sys_times(&tms);
+		/* Convert our struct tms to the compat version. */
+		tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime);
+		tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime);
+		tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime);
+		tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime);
 		if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
 			return -EFAULT;
 	}

kernel/exit.c

@@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, task_utime(tsk));
-		sig->stime = cputime_add(sig->stime, task_stime(tsk));
 		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
@@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
 		task_io_accounting_add(&sig->ioac, &tsk->ioac);
-		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
 
@@ -1301,6 +1298,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	if (likely(!traced)) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
+		struct task_cputime cputime;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1316,20 +1314,23 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * need to protect the access to p->parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_cputime() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
 		 */
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
+		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(p->utime,
-			cputime_add(sig->utime,
-				    sig->cutime)));
+			cputime_add(cputime.utime,
+				    sig->cutime));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(p->stime,
-			cputime_add(sig->stime,
-				    sig->cstime)));
+			cputime_add(cputime.stime,
+				    sig->cstime));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,

kernel/fork.c

@@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand)
 		kmem_cache_free(sighand_cachep, sighand);
 }
 
+
+/*
+ * Initialize POSIX timer handling for a thread group.
+ */
+static void posix_cpu_timers_init_group(struct signal_struct *sig)
+{
+	/* Thread group counters. */
+	thread_group_cputime_init(sig);
+
+	/* Expiration times and increments. */
+	sig->it_virt_expires = cputime_zero;
+	sig->it_virt_incr = cputime_zero;
+	sig->it_prof_expires = cputime_zero;
+	sig->it_prof_incr = cputime_zero;
+
+	/* Cached expiration times. */
+	sig->cputime_expires.prof_exp = cputime_zero;
+	sig->cputime_expires.virt_exp = cputime_zero;
+	sig->cputime_expires.sched_exp = 0;
+
+	/* The timer lists. */
+	INIT_LIST_HEAD(&sig->cpu_timers[0]);
+	INIT_LIST_HEAD(&sig->cpu_timers[1]);
+	INIT_LIST_HEAD(&sig->cpu_timers[2]);
+}
+
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
+		ret = thread_group_cputime_clone_thread(current);
+		if (likely(!ret)) {
 			atomic_inc(&current->signal->count);
 			atomic_inc(&current->signal->live);
-		return 0;
+		}
+		return ret;
 	}
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
@@ -795,40 +824,25 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->it_real_incr.tv64 = 0;
 	sig->real_timer.function = it_real_fn;
 
-	sig->it_virt_expires = cputime_zero;
-	sig->it_virt_incr = cputime_zero;
-	sig->it_prof_expires = cputime_zero;
-	sig->it_prof_incr = cputime_zero;
-
 	sig->leader = 0;	/* session leadership doesn't inherit */
 	sig->tty_old_pgrp = NULL;
 	sig->tty = NULL;
 
-	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
+	sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
 	task_io_accounting_init(&sig->ioac);
-	sig->sum_sched_runtime = 0;
-	INIT_LIST_HEAD(&sig->cpu_timers[0]);
-	INIT_LIST_HEAD(&sig->cpu_timers[1]);
-	INIT_LIST_HEAD(&sig->cpu_timers[2]);
 	taskstats_tgid_init(sig);
 
 	task_lock(current->group_leader);
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-		/*
-		 * New sole thread in the process gets an expiry time
-		 * of the whole CPU time limit.
-		 */
-		tsk->it_prof_expires =
-			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-	}
+	posix_cpu_timers_init_group(sig);
+
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
@@ -838,6 +852,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_signal(struct signal_struct *sig)
 {
+	thread_group_cputime_free(sig);
 	exit_thread_group_keys(sig);
 	tty_kref_put(sig->tty);
 	kmem_cache_free(signal_cachep, sig);
@@ -887,6 +902,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 }
 #endif /* CONFIG_MM_OWNER */
 
+/*
+ * Initialize POSIX timer handling for a single task.
+ */
+static void posix_cpu_timers_init(struct task_struct *tsk)
+{
+	tsk->cputime_expires.prof_exp = cputime_zero;
+	tsk->cputime_expires.virt_exp = cputime_zero;
+	tsk->cputime_expires.sched_exp = 0;
+	INIT_LIST_HEAD(&tsk->cpu_timers[0]);
+	INIT_LIST_HEAD(&tsk->cpu_timers[1]);
+	INIT_LIST_HEAD(&tsk->cpu_timers[2]);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -997,12 +1025,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 
-	p->it_virt_expires = cputime_zero;
-	p->it_prof_expires = cputime_zero;
-	p->it_sched_expires = 0;
-	INIT_LIST_HEAD(&p->cpu_timers[0]);
-	INIT_LIST_HEAD(&p->cpu_timers[1]);
-	INIT_LIST_HEAD(&p->cpu_timers[2]);
+	posix_cpu_timers_init(p);
 
 	p->lock_depth = -1;		/* -1 = no lock */
 	do_posix_clock_monotonic_gettime(&p->start_time);
@@ -1203,21 +1226,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (clone_flags & CLONE_THREAD) {
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-
-		if (!cputime_eq(current->signal->it_virt_expires,
-				cputime_zero) ||
-		    !cputime_eq(current->signal->it_prof_expires,
-				cputime_zero) ||
-		    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
-		    !list_empty(&current->signal->cpu_timers[0]) ||
-		    !list_empty(&current->signal->cpu_timers[1]) ||
-		    !list_empty(&current->signal->cpu_timers[2])) {
-			/*
-			 * Have child wake up on its first tick to check
-			 * for process CPU timers.
-			 */
-			p->it_prof_expires = jiffies_to_cputime(1);
-		}
 	}
 
 	if (likely(p->pid)) {

kernel/hrtimer.c

@@ -1403,9 +1403,7 @@ void hrtimer_run_queues(void)
 		if (!base->first)
 			continue;
 
-		if (base->get_softirq_time)
-			base->softirq_time = base->get_softirq_time();
-		else if (gettime) {
+		if (gettime) {
 			hrtimer_get_softirq_time(cpu_base);
 			gettime = 0;
 		}
@@ -1688,9 +1686,11 @@ static void migrate_hrtimers(int cpu)
 	new_base = &get_cpu_var(hrtimer_bases);
 
 	tick_cancel_sched_timer(cpu);
-
-	local_irq_disable();
-	spin_lock(&new_base->lock);
+	/*
+	 * The caller is globally serialized and nobody else
+	 * takes two locks at once, deadlock is not possible.
+	 */
+	spin_lock_irq(&new_base->lock);
 	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
@@ -1703,8 +1703,7 @@ static void migrate_hrtimers(int cpu)
 		raise = 1;
 
 	spin_unlock(&old_base->lock);
-	spin_unlock(&new_base->lock);
-	local_irq_enable();
+	spin_unlock_irq(&new_base->lock);
 	put_cpu_var(hrtimer_bases);
 
 	if (raise)

kernel/itimer.c

@@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value)
 		spin_unlock_irq(&tsk->sighand->siglock);
 		break;
 	case ITIMER_VIRTUAL:
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_virt_expires;
 		cinterval = tsk->signal->it_virt_incr;
 		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_struct *t = tsk;
-			cputime_t utime = tsk->signal->utime;
-			do {
-				utime = cputime_add(utime, t->utime);
-				t = next_thread(t);
-			} while (t != tsk);
+			struct task_cputime cputime;
+			cputime_t utime;
+
+			thread_group_cputime(tsk, &cputime);
+			utime = cputime.utime;
 			if (cputime_le(cval, utime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
 			} else {
@@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value)
 			}
 		}
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		cputime_to_timeval(cval, &value->it_value);
 		cputime_to_timeval(cinterval, &value->it_interval);
 		break;
 	case ITIMER_PROF:
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_prof_expires;
 		cinterval = tsk->signal->it_prof_incr;
 		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_struct *t = tsk;
-			cputime_t ptime = cputime_add(tsk->signal->utime,
-						      tsk->signal->stime);
-			do {
-				ptime = cputime_add(ptime,
-						    cputime_add(t->utime,
-								t->stime));
-				t = next_thread(t);
-			} while (t != tsk);
+			struct task_cputime times;
+			cputime_t ptime;
+
+			thread_group_cputime(tsk, &times);
+			ptime = cputime_add(times.utime, times.stime);
 			if (cputime_le(cval, ptime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
 			} else {
@@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value)
 			}
 		}
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		cputime_to_timeval(cval, &value->it_value);
 		cputime_to_timeval(cinterval, &value->it_interval);
 		break;
@@ -185,7 +176,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 	case ITIMER_VIRTUAL:
 		nval = timeval_to_cputime(&value->it_value);
 		ninterval = timeval_to_cputime(&value->it_interval);
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_virt_expires;
 		cinterval = tsk->signal->it_virt_incr;
@@ -200,7 +190,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 		tsk->signal->it_virt_expires = nval;
 		tsk->signal->it_virt_incr = ninterval;
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		if (ovalue) {
 			cputime_to_timeval(cval, &ovalue->it_value);
 			cputime_to_timeval(cinterval, &ovalue->it_interval);
@@ -209,7 +198,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 	case ITIMER_PROF:
 		nval = timeval_to_cputime(&value->it_value);
 		ninterval = timeval_to_cputime(&value->it_interval);
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_prof_expires;
 		cinterval = tsk->signal->it_prof_incr;
@@ -224,7 +212,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
 		tsk->signal->it_prof_expires = nval;
 		tsk->signal->it_prof_incr = ninterval;
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		if (ovalue) {
 			cputime_to_timeval(cval, &ovalue->it_value);
 			cputime_to_timeval(cinterval, &ovalue->it_interval);

kernel/posix-timers.c

@@ -222,6 +222,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+/*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+	getrawmonotonic(tp);
+	return 0;
+}
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
@@ -235,9 +244,15 @@ static __init int init_posix_timers(void)
 		.clock_get = posix_ktime_get_ts,
 		.clock_set = do_posix_clock_nosettime,
 	};
+	struct k_clock clock_monotonic_raw = {
+		.clock_getres = hrtimer_get_res,
+		.clock_get = posix_get_monotonic_raw,
+		.clock_set = do_posix_clock_nosettime,
+	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
 	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
+	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
@@ -298,6 +313,7 @@ void do_schedule_next_timer(struct siginfo *info)
 
 int posix_timer_event(struct k_itimer *timr, int si_private)
 {
+	int shared, ret;
 	/*
 	 * FIXME: if ->sigq is queued we can race with
 	 * dequeue_signal()->do_schedule_next_timer().
@@ -311,25 +327,10 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
 	 */
 	timr->sigq->info.si_sys_private = si_private;
 
-	timr->sigq->info.si_signo = timr->it_sigev_signo;
-	timr->sigq->info.si_code = SI_TIMER;
-	timr->sigq->info.si_tid = timr->it_id;
-	timr->sigq->info.si_value = timr->it_sigev_value;
-
-	if (timr->it_sigev_notify & SIGEV_THREAD_ID) {
-		struct task_struct *leader;
-		int ret = send_sigqueue(timr->sigq, timr->it_process, 0);
-
-		if (likely(ret >= 0))
-			return ret;
-
-		timr->it_sigev_notify = SIGEV_SIGNAL;
-		leader = timr->it_process->group_leader;
-		put_task_struct(timr->it_process);
-		timr->it_process = leader;
-	}
-
-	return send_sigqueue(timr->sigq, timr->it_process, 1);
+	shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+	ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+	/* If we failed to send the signal the timer stops. */
+	return ret > 0;
 }
 EXPORT_SYMBOL_GPL(posix_timer_event);
 
@@ -468,11 +469,9 @@ sys_timer_create(const clockid_t which_clock,
 		 struct sigevent __user *timer_event_spec,
 		 timer_t __user * created_timer_id)
 {
-	int error = 0;
-	struct k_itimer *new_timer = NULL;
-	int new_timer_id;
-	struct task_struct *process = NULL;
-	unsigned long flags;
+	struct k_itimer *new_timer;
+	int error, new_timer_id;
+	struct task_struct *process;
 	sigevent_t event;
 	int it_id_set = IT_ID_NOT_SET;
 
@@ -490,12 +489,11 @@ sys_timer_create(const clockid_t which_clock,
 		goto out;
 	}
 	spin_lock_irq(&idr_lock);
-	error = idr_get_new(&posix_timers_id, (void *) new_timer,
-			    &new_timer_id);
+	error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id);
 	spin_unlock_irq(&idr_lock);
+	if (error) {
 		if (error == -EAGAIN)
 			goto retry;
-	else if (error) {
 		/*
 		 * Weird looking, but we return EAGAIN if the IDR is
 		 * full (proper POSIX return value for this)
@@ -526,67 +524,43 @@ sys_timer_create(const clockid_t which_clock,
 			error = -EFAULT;
 			goto out;
 		}
-		new_timer->it_sigev_notify = event.sigev_notify;
-		new_timer->it_sigev_signo = event.sigev_signo;
-		new_timer->it_sigev_value = event.sigev_value;
-
-		read_lock(&tasklist_lock);
-		if ((process = good_sigevent(&event))) {
-			/*
-			 * We may be setting up this process for another
-			 * thread.  It may be exiting.  To catch this
-			 * case the we check the PF_EXITING flag.  If
-			 * the flag is not set, the siglock will catch
-			 * him before it is too late (in exit_itimers).
-			 *
-			 * The exec case is a bit more invloved but easy
-			 * to code.  If the process is in our thread
-			 * group (and it must be or we would not allow
-			 * it here) and is doing an exec, it will cause
-			 * us to be killed.  In this case it will wait
-			 * for us to die which means we can finish this
-			 * linkage with our last gasp. I.e. no code :)
-			 */
-			spin_lock_irqsave(&process->sighand->siglock, flags);
-			if (!(process->flags & PF_EXITING)) {
-				new_timer->it_process = process;
-				list_add(&new_timer->list,
-					 &process->signal->posix_timers);
-				if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
+		rcu_read_lock();
+		process = good_sigevent(&event);
+		if (process)
 			get_task_struct(process);
-				spin_unlock_irqrestore(&process->sighand->siglock, flags);
-			} else {
-				spin_unlock_irqrestore(&process->sighand->siglock, flags);
-				process = NULL;
-			}
-		}
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 		if (!process) {
 			error = -EINVAL;
 			goto out;
 		}
 	} else {
-		new_timer->it_sigev_notify = SIGEV_SIGNAL;
-		new_timer->it_sigev_signo = SIGALRM;
-		new_timer->it_sigev_value.sival_int = new_timer->it_id;
+		event.sigev_notify = SIGEV_SIGNAL;
+		event.sigev_signo = SIGALRM;
+		event.sigev_value.sival_int = new_timer->it_id;
 		process = current->group_leader;
-		spin_lock_irqsave(&process->sighand->siglock, flags);
-		new_timer->it_process = process;
-		list_add(&new_timer->list, &process->signal->posix_timers);
-		spin_unlock_irqrestore(&process->sighand->siglock, flags);
+		get_task_struct(process);
 	}
 
+	new_timer->it_sigev_notify     = event.sigev_notify;
+	new_timer->sigq->info.si_signo = event.sigev_signo;
+	new_timer->sigq->info.si_value = event.sigev_value;
+	new_timer->sigq->info.si_tid   = new_timer->it_id;
+	new_timer->sigq->info.si_code  = SI_TIMER;
+
+	spin_lock_irq(&current->sighand->siglock);
+	new_timer->it_process = process;
+	list_add(&new_timer->list, &current->signal->posix_timers);
+	spin_unlock_irq(&current->sighand->siglock);
+
+	return 0;
  	/*
 	 * In the case of the timer belonging to another task, after
 	 * the task is unlocked, the timer is owned by the other task
 	 * and may cease to exist at any time.  Don't use or modify
 	 * new_timer after the unlock call.
 	 */
-
 out:
-	if (error)
 	release_posix_timer(new_timer, it_id_set);
-
 	return error;
 }
 
@@ -597,7 +571,7 @@ sys_timer_create(const clockid_t which_clock,
  * the find to the timer lock.  To avoid a dead lock, the timer id MUST
  * be release with out holding the timer lock.
  */
-static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
+static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
 {
 	struct k_itimer *timr;
 	/*
@@ -605,23 +579,20 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags)
 	 * flags part over to the timer lock.  Must not let interrupts in
 	 * while we are moving the lock.
 	 */
-
 	spin_lock_irqsave(&idr_lock, *flags);
-	timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id);
+	timr = idr_find(&posix_timers_id, (int)timer_id);
 	if (timr) {
 		spin_lock(&timr->it_lock);
-
-		if ((timr->it_id != timer_id) || !(timr->it_process) ||
-				!same_thread_group(timr->it_process, current)) {
-			spin_unlock(&timr->it_lock);
-			spin_unlock_irqrestore(&idr_lock, *flags);
-			timr = NULL;
-		} else
+		if (timr->it_process &&
+		    same_thread_group(timr->it_process, current)) {
 			spin_unlock(&idr_lock);
-	} else
+			return timr;
+		}
+		spin_unlock(&timr->it_lock);
+	}
 	spin_unlock_irqrestore(&idr_lock, *flags);
 
-	return timr;
+	return NULL;
 }
 
 /*
@@ -862,7 +833,6 @@ sys_timer_delete(timer_t timer_id)
 	 * This keeps any tasks waiting on the spin lock from thinking
 	 * they got something (see the lock code above).
 	 */
-	if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
 	put_task_struct(timer->it_process);
 	timer->it_process = NULL;
 
@@ -890,7 +860,6 @@ static void itimer_delete(struct k_itimer *timer)
 	 * This keeps any tasks waiting on the spin lock from thinking
 	 * they got something (see the lock code above).
 	 */
-	if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID))
 	put_task_struct(timer->it_process);
 	timer->it_process = NULL;
 

kernel/sched.c

@@ -4052,23 +4052,26 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
 EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
- * Return p->sum_exec_runtime plus any more ns on the sched_clock
- * that have not yet been banked in case the task is currently running.
+ * Return any ns on the sched_clock that have not yet been banked in
+ * @p in case that task is currently running.
  */
-unsigned long long task_sched_runtime(struct task_struct *p)
+unsigned long long task_delta_exec(struct task_struct *p)
 {
 	unsigned long flags;
-	u64 ns, delta_exec;
 	struct rq *rq;
+	u64 ns = 0;
 
 	rq = task_rq_lock(p, &flags);
-	ns = p->se.sum_exec_runtime;
+
 	if (task_current(rq, p)) {
+		u64 delta_exec;
+
 		update_rq_clock(rq);
 		delta_exec = rq->clock - p->se.exec_start;
 		if ((s64)delta_exec > 0)
-			ns += delta_exec;
+			ns = delta_exec;
 	}
+
 	task_rq_unlock(rq, &flags);
 
 	return ns;
@@ -4085,6 +4088,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
 	cputime64_t tmp;
 
 	p->utime = cputime_add(p->utime, cputime);
+	account_group_user_time(p, cputime);
 
 	/* Add user time to cpustat. */
 	tmp = cputime_to_cputime64(cputime);
@@ -4109,6 +4113,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
 	tmp = cputime_to_cputime64(cputime);
 
 	p->utime = cputime_add(p->utime, cputime);
+	account_group_user_time(p, cputime);
 	p->gtime = cputime_add(p->gtime, cputime);
 
 	cpustat->user = cputime64_add(cpustat->user, tmp);
@@ -4144,6 +4149,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	}
 
 	p->stime = cputime_add(p->stime, cputime);
+	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
 	tmp = cputime_to_cputime64(cputime);
@@ -4185,6 +4191,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
 	if (p == rq->idle) {
 		p->stime = cputime_add(p->stime, steal);
+		account_group_system_time(p, steal);
 		if (atomic_read(&rq->nr_iowait) > 0)
 			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 		else

kernel/sched_fair.c

@@ -449,6 +449,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 		struct task_struct *curtask = task_of(curr);
 
 		cpuacct_charge(curtask, delta_exec);
+		account_group_exec_runtime(curtask, delta_exec);
 	}
 }
 

kernel/sched_rt.c

@@ -526,6 +526,8 @@ static void update_curr_rt(struct rq *rq)
 	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
@@ -1458,7 +1460,7 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 		p->rt.timeout++;
 		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
 		if (p->rt.timeout > next)
-			p->it_sched_expires = p->se.sum_exec_runtime;
+			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
 	}
 }
 

kernel/sched_stats.h

@@ -270,3 +270,89 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 #define sched_info_switch(t, next)		do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
 
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+/**
+ * account_group_user_time - Maintain utime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the utime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					   cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+		times->utime = cputime_add(times->utime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * account_group_system_time - Maintain stime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the stime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void account_group_system_time(struct task_struct *tsk,
+					     cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+		times->stime = cputime_add(times->stime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of the thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					      unsigned long long ns)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
+		times->sum_exec_runtime += ns;
+		put_cpu_no_resched();
+	}
+}

kernel/signal.c

@@ -1338,6 +1338,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	struct siginfo info;
 	unsigned long flags;
 	struct sighand_struct *psig;
+	struct task_cputime cputime;
 	int ret = sig;
 
 	BUG_ON(sig == -1);
@@ -1368,10 +1369,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	info.si_uid = tsk->uid;
 
-	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
-						       tsk->signal->utime));
-	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
-						       tsk->signal->stime));
+	thread_group_cputime(tsk, &cputime);
+	info.si_utime = cputime_to_jiffies(cputime.utime);
+	info.si_stime = cputime_to_jiffies(cputime.stime);
 
 	info.si_status = tsk->exit_code & 0x7f;
 	if (tsk->exit_code & 0x80)

kernel/softirq.c

@@ -267,16 +267,12 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-#ifdef CONFIG_NO_HZ
 	int cpu = smp_processor_id();
+
 	if (idle_cpu(cpu) && !in_interrupt())
-		tick_nohz_stop_idle(cpu);
-#endif
+		tick_check_idle(cpu);
+
 	__irq_enter();
-#ifdef CONFIG_NO_HZ
-	if (idle_cpu(cpu))
-		tick_nohz_update_jiffies();
-#endif
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED

kernel/sys.c

@@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid)
 	return old_fsgid;
 }
 
+void do_sys_times(struct tms *tms)
+{
+	struct task_cputime cputime;
+	cputime_t cutime, cstime;
+
+	spin_lock_irq(&current->sighand->siglock);
+	thread_group_cputime(current, &cputime);
+	cutime = current->signal->cutime;
+	cstime = current->signal->cstime;
+	spin_unlock_irq(&current->sighand->siglock);
+	tms->tms_utime = cputime_to_clock_t(cputime.utime);
+	tms->tms_stime = cputime_to_clock_t(cputime.stime);
+	tms->tms_cutime = cputime_to_clock_t(cutime);
+	tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
 asmlinkage long sys_times(struct tms __user * tbuf)
 {
-	/*
-	 *	In the SMP world we might just be unlucky and have one of
-	 *	the times increment as we use it. Since the value is an
-	 *	atomically safe type this is just fine. Conceptually its
-	 *	as if the syscall took an instant longer to occur.
-	 */
 	if (tbuf) {
 		struct tms tmp;
-		struct task_struct *tsk = current;
-		struct task_struct *t;
-		cputime_t utime, stime, cutime, cstime;
 
-		spin_lock_irq(&tsk->sighand->siglock);
-		utime = tsk->signal->utime;
-		stime = tsk->signal->stime;
-		t = tsk;
-		do {
-			utime = cputime_add(utime, t->utime);
-			stime = cputime_add(stime, t->stime);
-			t = next_thread(t);
-		} while (t != tsk);
-
-		cutime = tsk->signal->cutime;
-		cstime = tsk->signal->cstime;
-		spin_unlock_irq(&tsk->sighand->siglock);
-
-		tmp.tms_utime = cputime_to_clock_t(utime);
-		tmp.tms_stime = cputime_to_clock_t(stime);
-		tmp.tms_cutime = cputime_to_clock_t(cutime);
-		tmp.tms_cstime = cputime_to_clock_t(cstime);
+		do_sys_times(&tmp);
 		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
 			return -EFAULT;
 	}
@@ -1449,7 +1439,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 {
 	struct rlimit new_rlim, *old_rlim;
-	unsigned long it_prof_secs;
 	int retval;
 
 	if (resource >= RLIM_NLIMITS)
@@ -1503,18 +1492,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 	if (new_rlim.rlim_cur == RLIM_INFINITY)
 		goto out;
 
-	it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
-	if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
-		unsigned long rlim_cur = new_rlim.rlim_cur;
-		cputime_t cputime;
-
-		cputime = secs_to_cputime(rlim_cur);
-		read_lock(&tasklist_lock);
-		spin_lock_irq(&current->sighand->siglock);
-		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-		spin_unlock_irq(&current->sighand->siglock);
-		read_unlock(&tasklist_lock);
-	}
+	update_rlimit_cpu(new_rlim.rlim_cur);
 out:
 	return 0;
 }
@@ -1552,11 +1530,8 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
  *
  */
 
-static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r,
-				     cputime_t *utimep, cputime_t *stimep)
+static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
 {
-	*utimep = cputime_add(*utimep, t->utime);
-	*stimep = cputime_add(*stimep, t->stime);
 	r->ru_nvcsw += t->nvcsw;
 	r->ru_nivcsw += t->nivcsw;
 	r->ru_minflt += t->min_flt;
@@ -1570,12 +1545,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	cputime_t utime, stime;
+	struct task_cputime cputime;
 
 	memset((char *) r, 0, sizeof *r);
 	utime = stime = cputime_zero;
 
 	if (who == RUSAGE_THREAD) {
-		accumulate_thread_rusage(p, r, &utime, &stime);
+		accumulate_thread_rusage(p, r);
 		goto out;
 	}
 
@@ -1598,8 +1574,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			utime = cputime_add(utime, p->signal->utime);
-			stime = cputime_add(stime, p->signal->stime);
+			thread_group_cputime(p, &cputime);
+			utime = cputime_add(utime, cputime.utime);
+			stime = cputime_add(stime, cputime.stime);
 			r->ru_nvcsw += p->signal->nvcsw;
 			r->ru_nivcsw += p->signal->nivcsw;
 			r->ru_minflt += p->signal->min_flt;
@@ -1608,7 +1585,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			r->ru_oublock += p->signal->oublock;
 			t = p;
 			do {
-				accumulate_thread_rusage(t, r, &utime, &stime);
+				accumulate_thread_rusage(t, r);
 				t = next_thread(t);
 			} while (t != p);
 			break;

kernel/time/clocksource.c

@@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c)
 	unsigned long flags;
 	int ret;
 
+	/* save mult_orig on registration */
+	c->mult_orig = c->mult;
+
 	spin_lock_irqsave(&clocksource_lock, flags);
 	ret = clocksource_enqueue(c);
 	if (!ret)

kernel/time/jiffies.c

@@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = {
 	.read		= jiffies_read,
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+	.mult_orig	= NSEC_PER_JIFFY << JIFFIES_SHIFT,
 	.shift		= JIFFIES_SHIFT,
 };
 

kernel/time/ntp.c

@@ -10,13 +10,13 @@
 
 #include <linux/mm.h>
 #include <linux/time.h>
-#include <linux/timer.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
 #include <linux/hrtimer.h>
 #include <linux/capability.h>
 #include <linux/math64.h>
 #include <linux/clocksource.h>
+#include <linux/workqueue.h>
 #include <asm/timex.h>
 
 /*
@@ -218,11 +218,11 @@ void second_overflow(void)
 /* Disable the cmos update - used by virtualization and embedded */
 int no_sync_cmos_clock  __read_mostly;
 
-static void sync_cmos_clock(unsigned long dummy);
+static void sync_cmos_clock(struct work_struct *work);
 
-static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
+static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
 
-static void sync_cmos_clock(unsigned long dummy)
+static void sync_cmos_clock(struct work_struct *work)
 {
 	struct timespec now, next;
 	int fail = 1;
@@ -258,13 +258,13 @@ static void sync_cmos_clock(unsigned long dummy)
 		next.tv_sec++;
 		next.tv_nsec -= NSEC_PER_SEC;
 	}
-	mod_timer(&sync_cmos_timer, jiffies + timespec_to_jiffies(&next));
+	schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
 static void notify_cmos_timer(void)
 {
 	if (!no_sync_cmos_clock)
-		mod_timer(&sync_cmos_timer, jiffies + 1);
+		schedule_delayed_work(&sync_cmos_work, 0);
 }
 
 #else
@@ -277,38 +277,50 @@ static inline void notify_cmos_timer(void) { }
 int do_adjtimex(struct timex *txc)
 {
 	struct timespec ts;
-	long save_adjust, sec;
 	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))
+			return -EINVAL;
+		if (!(txc->modes & ADJ_OFFSET_READONLY) &&
+		    !capable(CAP_SYS_TIME))
+			return -EPERM;
+	} else {
 		/* In order to modify anything, you gotta be super-user! */
 		 if (txc->modes && !capable(CAP_SYS_TIME))
 			return -EPERM;
 
-	/* Now we validate the data before disabling interrupts */
-
-	if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) {
-		/* singleshot must not be used with any other mode bits */
-		if (txc->modes & ~ADJ_OFFSET_SS_READ)
-			return -EINVAL;
-	}
-
-	/* if the quartz is off by more than 10% something is VERY wrong ! */
-	if (txc->modes & ADJ_TICK)
-		if (txc->tick <  900000/USER_HZ ||
-		    txc->tick > 1100000/USER_HZ)
+		/* if the quartz is off by more than 10% something is VERY wrong! */
+		if (txc->modes & ADJ_TICK &&
+		    (txc->tick <  900000/USER_HZ ||
+		     txc->tick > 1100000/USER_HZ))
 				return -EINVAL;
 
-	if (time_state != TIME_OK && txc->modes & ADJ_STATUS)
+		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
 			hrtimer_cancel(&leap_timer);
+	}
+
 	getnstimeofday(&ts);
 
 	write_seqlock_irq(&xtime_lock);
 
-	/* Save for later - semantics of adjtime is to return old value */
-	save_adjust = time_adjust;
-
 	/* If there are input parameters, then process them */
+	if (txc->modes & ADJ_ADJTIME) {
+		long save_adjust = time_adjust;
+
+		if (!(txc->modes & ADJ_OFFSET_READONLY)) {
+			/* adjtime() is independent from ntp_adjtime() */
+			time_adjust = txc->offset;
+			ntp_update_frequency();
+		}
+		txc->offset = save_adjust;
+		goto adj_done;
+	}
 	if (txc->modes) {
+		long sec;
+
 		if (txc->modes & ADJ_STATUS) {
 			if ((time_status & STA_PLL) &&
 			    !(txc->status & STA_PLL)) {
@@ -375,13 +387,8 @@ int do_adjtimex(struct timex *txc)
 		if (txc->modes & ADJ_TAI && txc->constant > 0)
 			time_tai = txc->constant;
 
-		if (txc->modes & ADJ_OFFSET) {
-			if (txc->modes == ADJ_OFFSET_SINGLESHOT)
-				/* adjtime() is independent from ntp_adjtime() */
-				time_adjust = txc->offset;
-			else
+		if (txc->modes & ADJ_OFFSET)
 			ntp_update_offset(txc->offset);
-		}
 		if (txc->modes & ADJ_TICK)
 			tick_usec = txc->tick;
 
@@ -389,22 +396,18 @@ int do_adjtimex(struct timex *txc)
 			ntp_update_frequency();
 	}
 
-	result = time_state;	/* mostly `TIME_OK' */
-	if (time_status & (STA_UNSYNC|STA_CLOCKERR))
-		result = TIME_ERROR;
-
-	if ((txc->modes == ADJ_OFFSET_SINGLESHOT) ||
-	    (txc->modes == ADJ_OFFSET_SS_READ))
-		txc->offset = save_adjust;
-	else {
 	txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
 	if (!(time_status & STA_NANO))
 		txc->offset /= NSEC_PER_USEC;
-	}
-	txc->freq	   = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) *
-					 (s64)PPM_SCALE_INV,
-					 NTP_SCALE_SHIFT);
+
+adj_done:
+	result = time_state;	/* mostly `TIME_OK' */
+	if (time_status & (STA_UNSYNC|STA_CLOCKERR))
+		result = TIME_ERROR;
+
+	txc->freq	   = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
+					 (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT);
 	txc->maxerror	   = time_maxerror;
 	txc->esterror	   = time_esterror;
 	txc->status	   = time_status;

kernel/time/tick-broadcast.c

@@ -383,6 +383,19 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 	return 0;
 }
 
+/*
+ * Called from irq_enter() when idle was interrupted to reenable the
+ * per cpu device.
+ */
+void tick_check_oneshot_broadcast(int cpu)
+{
+	if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+
+		clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+	}
+}
+
 /*
  * Handle oneshot mode broadcasting
  */

kernel/time/tick-internal.h

@@ -36,6 +36,7 @@ extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
+extern void tick_check_oneshot_broadcast(int cpu);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
@@ -45,6 +46,7 @@ static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
+static inline void tick_check_oneshot_broadcast(int cpu) { }
 # endif /* !BROADCAST */
 
 #else /* !ONESHOT */

kernel/time/tick-sched.c

@@ -155,7 +155,7 @@ void tick_nohz_update_jiffies(void)
 	touch_softlockup_watchdog();
 }
 
-void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
@@ -377,6 +377,32 @@ ktime_t tick_nohz_get_sleep_length(void)
 	return ts->sleep_length;
 }
 
+static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
+{
+	hrtimer_cancel(&ts->sched_timer);
+	ts->sched_timer.expires = ts->idle_tick;
+
+	while (1) {
+		/* Forward the time to expire in the future */
+		hrtimer_forward(&ts->sched_timer, now, tick_period);
+
+		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
+			hrtimer_start(&ts->sched_timer,
+				      ts->sched_timer.expires,
+				      HRTIMER_MODE_ABS);
+			/* Check, if the timer was already in the past */
+			if (hrtimer_active(&ts->sched_timer))
+				break;
+		} else {
+			if (!tick_program_event(ts->sched_timer.expires, 0))
+				break;
+		}
+		/* Update jiffies and reread time */
+		tick_do_update_jiffies64(now);
+		now = ktime_get();
+	}
+}
+
 /**
  * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
  *
@@ -430,28 +456,7 @@ void tick_nohz_restart_sched_tick(void)
 	 */
 	ts->tick_stopped  = 0;
 	ts->idle_exittime = now;
-	hrtimer_cancel(&ts->sched_timer);
-	ts->sched_timer.expires = ts->idle_tick;
-
-	while (1) {
-		/* Forward the time to expire in the future */
-		hrtimer_forward(&ts->sched_timer, now, tick_period);
-
-		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
-			hrtimer_start(&ts->sched_timer,
-				      ts->sched_timer.expires,
-				      HRTIMER_MODE_ABS);
-			/* Check, if the timer was already in the past */
-			if (hrtimer_active(&ts->sched_timer))
-				break;
-		} else {
-			if (!tick_program_event(ts->sched_timer.expires, 0))
-				break;
-		}
-		/* Update jiffies and reread time */
-		tick_do_update_jiffies64(now);
-		now = ktime_get();
-	}
+	tick_nohz_restart(ts, now);
 	local_irq_enable();
 }
 
@@ -503,10 +508,6 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	update_process_times(user_mode(regs));
 	profile_tick(CPU_PROFILING);
 
-	/* Do not restart, when we are in the idle loop */
-	if (ts->tick_stopped)
-		return;
-
 	while (tick_nohz_reprogram(ts, now)) {
 		now = ktime_get();
 		tick_do_update_jiffies64(now);
@@ -552,12 +553,46 @@ static void tick_nohz_switch_to_nohz(void)
 	       smp_processor_id());
 }
 
+/*
+ * When NOHZ is enabled and the tick is stopped, we need to kick the
+ * tick timer from irq_enter() so that the jiffies update is kept
+ * alive during long running softirqs. That's ugly as hell, but
+ * correctness is key even if we need to fix the offending softirq in
+ * the first place.
+ *
+ * Note, this is different to tick_nohz_restart. We just kick the
+ * timer and do not touch the other magic bits which need to be done
+ * when idle is left.
+ */
+static void tick_nohz_kick_tick(int cpu)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (!ts->tick_stopped)
+		return;
+
+	tick_nohz_restart(ts, ktime_get());
+}
+
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
 
 #endif /* NO_HZ */
 
+/*
+ * Called from irq_enter to notify about the possible interruption of idle()
+ */
+void tick_check_idle(int cpu)
+{
+	tick_check_oneshot_broadcast(cpu);
+#ifdef CONFIG_NO_HZ
+	tick_nohz_stop_idle(cpu);
+	tick_nohz_update_jiffies();
+	tick_nohz_kick_tick(cpu);
+#endif
+}
+
 /*
  * High resolution timer specific code
  */
@@ -611,10 +646,6 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 		profile_tick(CPU_PROFILING);
 	}
 
-	/* Do not restart, when we are in the idle loop */
-	if (ts->tick_stopped)
-		return HRTIMER_NORESTART;
-
 	hrtimer_forward(timer, now, tick_period);
 
 	return HRTIMER_RESTART;

kernel/time/timekeeping.c

@@ -58,27 +58,26 @@ struct clocksource *clock;
 
 #ifdef CONFIG_GENERIC_TIME
 /**
- * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook
+ * clocksource_forward_now - update clock to the current time
  *
- * private function, must hold xtime_lock lock when being
- * called. Returns the number of nanoseconds since the
- * last call to update_wall_time() (adjusted by NTP scaling)
+ * Forward the current clock to update its state since the last call to
+ * update_wall_time(). This is useful before significant clock changes,
+ * as it avoids having to deal with this time offset explicitly.
  */
-static inline s64 __get_nsec_offset(void)
+static void clocksource_forward_now(void)
 {
 	cycle_t cycle_now, cycle_delta;
-	s64 ns_offset;
+	s64 nsec;
 
-	/* read clocksource: */
 	cycle_now = clocksource_read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+	clock->cycle_last = cycle_now;
 
-	/* convert to nanoseconds: */
-	ns_offset = cyc2ns(clock, cycle_delta);
+	nsec = cyc2ns(clock, cycle_delta);
+	timespec_add_ns(&xtime, nsec);
 
-	return ns_offset;
+	nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+	clock->raw_time.tv_nsec += nsec;
 }
 
 /**
@@ -89,6 +88,7 @@ static inline s64 __get_nsec_offset(void)
  */
 void getnstimeofday(struct timespec *ts)
 {
+	cycle_t cycle_now, cycle_delta;
 	unsigned long seq;
 	s64 nsecs;
 
@@ -96,7 +96,15 @@ void getnstimeofday(struct timespec *ts)
 		seq = read_seqbegin(&xtime_lock);
 
 		*ts = xtime;
-		nsecs = __get_nsec_offset();
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = cyc2ns(clock, cycle_delta);
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -129,22 +137,22 @@ EXPORT_SYMBOL(do_gettimeofday);
  */
 int do_settimeofday(struct timespec *tv)
 {
+	struct timespec ts_delta;
 	unsigned long flags;
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
 
 	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
-	nsec -= __get_nsec_offset();
+	clocksource_forward_now();
 
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+	ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
+	ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
+
+	xtime = *tv;
 
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
 	update_xtime_cache(0);
 
 	clock->error = 0;
@@ -170,22 +178,19 @@ EXPORT_SYMBOL(do_settimeofday);
 static void change_clocksource(void)
 {
 	struct clocksource *new;
-	cycle_t now;
-	u64 nsec;
 
 	new = clocksource_get_next();
 
 	if (clock == new)
 		return;
 
-	new->cycle_last = 0;
-	now = clocksource_read(new);
-	nsec =  __get_nsec_offset();
-	timespec_add_ns(&xtime, nsec);
+	clocksource_forward_now();
 
-	clock = new;
-	clock->cycle_last = now;
+	new->raw_time = clock->raw_time;
 
+	clock = new;
+	clock->cycle_last = 0;
+	clock->cycle_last = clocksource_read(new);
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -200,10 +205,43 @@ static void change_clocksource(void)
 	 */
 }
 #else
+static inline void clocksource_forward_now(void) { }
 static inline void change_clocksource(void) { }
-static inline s64 __get_nsec_offset(void) { return 0; }
 #endif
 
+/**
+ * getrawmonotonic - Returns the raw monotonic time in a timespec
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the raw monotonic time (completely un-modified by ntp)
+ */
+void getrawmonotonic(struct timespec *ts)
+{
+	unsigned long seq;
+	s64 nsecs;
+	cycle_t cycle_now, cycle_delta;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+
+		*ts = clock->raw_time;
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	timespec_add_ns(ts, nsecs);
+}
+EXPORT_SYMBOL(getrawmonotonic);
+
+
 /**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
  */
@@ -265,8 +303,6 @@ void __init timekeeping_init(void)
 static int timekeeping_suspended;
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
-/* xtime offset when we went into suspend */
-static s64 timekeeping_suspend_nsecs;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -292,8 +328,6 @@ static int timekeeping_resume(struct sys_device *dev)
 		wall_to_monotonic.tv_sec -= sleep_length;
 		total_sleep_time += sleep_length;
 	}
-	/* Make sure that we have the correct xtime reference */
-	timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
 	update_xtime_cache(0);
 	/* re-base the last cycle value */
 	clock->cycle_last = 0;
@@ -319,8 +353,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 	timekeeping_suspend_time = read_persistent_clock();
 
 	write_seqlock_irqsave(&xtime_lock, flags);
-	/* Get the current xtime offset */
-	timekeeping_suspend_nsecs = __get_nsec_offset();
+	clocksource_forward_now();
 	timekeeping_suspended = 1;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -454,23 +487,29 @@ void update_wall_time(void)
 #else
 	offset = clock->cycle_interval;
 #endif
-	clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift;
+	clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift;
 
 	/* normally this loop will run just once, however in the
 	 * case of lost or late ticks, it will accumulate correctly.
 	 */
 	while (offset >= clock->cycle_interval) {
 		/* accumulate one interval */
-		clock->xtime_nsec += clock->xtime_interval;
-		clock->cycle_last += clock->cycle_interval;
 		offset -= clock->cycle_interval;
+		clock->cycle_last += clock->cycle_interval;
 
+		clock->xtime_nsec += clock->xtime_interval;
 		if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
 			clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
 			xtime.tv_sec++;
 			second_overflow();
 		}
 
+		clock->raw_time.tv_nsec += clock->raw_interval;
+		if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) {
+			clock->raw_time.tv_nsec -= NSEC_PER_SEC;
+			clock->raw_time.tv_sec++;
+		}
+
 		/* accumulate error between NTP and clock interval */
 		clock->error += tick_length;
 		clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);
@@ -479,9 +518,12 @@ void update_wall_time(void)
 	/* correct the clock when NTP error is too big */
 	clocksource_adjust(offset);
 
-	/* store full nanoseconds into xtime */
-	xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift;
+	/* store full nanoseconds into xtime after rounding it up and
+	 * add the remainder to the error difference.
+	 */
+	xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1;
 	clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift;
+	clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift);
 
 	update_xtime_cache(cyc2ns(clock, offset));
 

kernel/time/timer_list.c

@@ -47,13 +47,14 @@ static void print_name_offset(struct seq_file *m, void *sym)
 }
 
 static void
-print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now)
+print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
+	    int idx, u64 now)
 {
 #ifdef CONFIG_TIMER_STATS
 	char tmp[TASK_COMM_LEN + 1];
 #endif
 	SEQ_printf(m, " #%d: ", idx);
-	print_name_offset(m, timer);
+	print_name_offset(m, taddr);
 	SEQ_printf(m, ", ");
 	print_name_offset(m, timer->function);
 	SEQ_printf(m, ", S:%02lx", timer->state);
@@ -99,7 +100,7 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 		tmp = *timer;
 		spin_unlock_irqrestore(&base->cpu_base->lock, flags);
 
-		print_timer(m, &tmp, i, now);
+		print_timer(m, timer, &tmp, i, now);
 		next++;
 		goto next_one;
 	}
@@ -109,6 +110,7 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
 static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
+	SEQ_printf(m, "  .base:       %p\n", base);
 	SEQ_printf(m, "  .index:      %d\n",
 			base->index);
 	SEQ_printf(m, "  .resolution: %Lu nsecs\n",
@@ -183,12 +185,16 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 static void
-print_tickdevice(struct seq_file *m, struct tick_device *td)
+print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 {
 	struct clock_event_device *dev = td->evtdev;
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
+	if (cpu < 0)
+		SEQ_printf(m, "Broadcast device\n");
+	else
+		SEQ_printf(m, "Per CPU device: %d\n", cpu);
 
 	SEQ_printf(m, "Clock Event Device: ");
 	if (!dev) {
@@ -222,7 +228,7 @@ static void timer_list_show_tickdevices(struct seq_file *m)
 	int cpu;
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
-	print_tickdevice(m, tick_get_broadcast_device());
+	print_tickdevice(m, tick_get_broadcast_device(), -1);
 	SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
 		   tick_get_broadcast_mask()->bits[0]);
 #ifdef CONFIG_TICK_ONESHOT
@@ -232,7 +238,7 @@ static void timer_list_show_tickdevices(struct seq_file *m)
 	SEQ_printf(m, "\n");
 #endif
 	for_each_online_cpu(cpu)
-		   print_tickdevice(m, tick_get_device(cpu));
+		print_tickdevice(m, tick_get_device(cpu), cpu);
 	SEQ_printf(m, "\n");
 }
 #else
@@ -244,7 +250,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.3\n");
+	SEQ_printf(m, "Timer List Version: v0.4\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 

kernel/timer.c

@@ -1436,9 +1436,11 @@ static void __cpuinit migrate_timers(int cpu)
 	BUG_ON(cpu_online(cpu));
 	old_base = per_cpu(tvec_bases, cpu);
 	new_base = get_cpu_var(tvec_bases);
-
-	local_irq_disable();
-	spin_lock(&new_base->lock);
+	/*
+	 * The caller is globally serialized and nobody else
+	 * takes two locks at once, deadlock is not possible.
+	 */
+	spin_lock_irq(&new_base->lock);
 	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
 	BUG_ON(old_base->running_timer);
@@ -1453,8 +1455,7 @@ static void __cpuinit migrate_timers(int cpu)
 	}
 
 	spin_unlock(&old_base->lock);
-	spin_unlock(&new_base->lock);
-	local_irq_enable();
+	spin_unlock_irq(&new_base->lock);
 	put_cpu_var(tvec_bases);
 }
 #endif /* CONFIG_HOTPLUG_CPU */

security/selinux/hooks.c

@@ -75,6 +75,7 @@
 #include <linux/string.h>
 #include <linux/selinux.h>
 #include <linux/mutex.h>
+#include <linux/posix-timers.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -2322,13 +2323,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm)
 			initrlim = init_task.signal->rlim+i;
 			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
 		}
-		if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-			/*
-			 * This will cause RLIMIT_CPU calculations
-			 * to be refigured.
-			 */
-			current->it_prof_expires = jiffies_to_cputime(1);
-		}
+		update_rlimit_cpu(rlim->rlim_cur);
 	}
 
 	/* Wake up the parent if it is waiting so that it can