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
2026-03-06 15:25:10 -08:00 · 2008-10-20 13:19:56 -07:00
parent 72558dde73 c465a76af6
commit 99ebcf8285
37 changed files with 908 additions and 726 deletions
--- a/Documentation/sysrq.txt
+++ b/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.

--- a/drivers/char/sysrq.c
+++ b/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)
--- a/drivers/clocksource/acpi_pm.c
+++ b/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;
--- a/fs/binfmt_elf.c
+++ b/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);
--- a/fs/proc/array.c
+++ b/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);
 		}

--- a/include/linux/clocksource.h
+++ b/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;
 }


--- a/include/linux/hrtimer.h
+++ b/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
 };

--- a/include/linux/kernel_stat.h
+++ b/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);
--- a/include/linux/posix-timers.h
+++ b/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
--- a/include/linux/sched.h
+++ b/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.
--- a/include/linux/tick.h
+++ b/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 */

--- a/include/linux/time.h
+++ b/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:
--- a/include/linux/timex.h
+++ b/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
--- a/kernel/compat.c
+++ b/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;
 	}
--- a/kernel/exit.c
+++ b/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,
--- a/kernel/fork.c
+++ b/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) {
-		atomic_inc(&current->signal->count);
-		atomic_inc(&current->signal->live);
-		return 0;
+		ret = thread_group_cputime_clone_thread(current);
+		if (likely(!ret)) {
+			atomic_inc(&current->signal->count);
+			atomic_inc(&current->signal->live);
+		}
+		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)) {
--- a/kernel/hrtimer.c
+++ b/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)
--- a/kernel/itimer.c
+++ b/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 @@ again:
 	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 @@ again:
 		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 @@ again:
 	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 @@ again:
 		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);
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
--- a/kernel/posix-timers.c
+++ b/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 == -EAGAIN)
-		goto retry;
-	else if (error) {
+	if (error) {
+		if (error == -EAGAIN)
+			goto retry;
 		/*
 		 * 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))
-					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_lock();
+		process = good_sigevent(&event);
+		if (process)
+			get_task_struct(process);
+		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);
-
+	release_posix_timer(new_timer, it_id_set);
 	return error;
 }

@@ -597,7 +571,7 @@ out:
 * 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
-		spin_unlock_irqrestore(&idr_lock, *flags);
+			return timr;
+		}
+		spin_unlock(&timr->it_lock);
+	}
+	spin_unlock_irqrestore(&idr_lock, *flags);

-	return timr;
+	return NULL;
 }

 /*
@@ -862,8 +833,7 @@ retry_delete:
 	 * 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);
+	put_task_struct(timer->it_process);
 	timer->it_process = NULL;

 	unlock_timer(timer, flags);
@@ -890,8 +860,7 @@ retry_delete:
 	 * 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);
+	put_task_struct(timer->it_process);
 	timer->it_process = NULL;

 	unlock_timer(timer, flags);
--- a/Show More
+++ b/Show More