Merge branch 'v28-timers-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/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 */
 
 	/*
@@ -509,22 +553,14 @@ 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;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	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

@@ -96,36 +96,35 @@ 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 */
 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 */