summaryrefslogtreecommitdiffstats
path: root/kernel/time
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2014-06-22 12:06:40 +0200
committerThomas Gleixner <tglx@linutronix.de>2014-06-23 11:22:35 +0200
commit5cee964597260237dd2cabb3ec22bba0da24b25d (patch)
treef548efb4181a4cffb026adf43178e65330533e87 /kernel/time
parent58394271c610e9c65dd0165a1c1f6dec75dc5f3e (diff)
downloadlinux-5cee964597260237dd2cabb3ec22bba0da24b25d.tar.gz
linux-5cee964597260237dd2cabb3ec22bba0da24b25d.tar.bz2
linux-5cee964597260237dd2cabb3ec22bba0da24b25d.zip
time/timers: Move all time(r) related files into kernel/time
Except for Kconfig.HZ. That needs a separate treatment. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Makefile17
-rw-r--r--kernel/time/hrtimer.c1915
-rw-r--r--kernel/time/itimer.c301
-rw-r--r--kernel/time/posix-cpu-timers.c1490
-rw-r--r--kernel/time/posix-timers.c1121
-rw-r--r--kernel/time/time.c714
-rw-r--r--kernel/time/timeconst.bc108
-rw-r--r--kernel/time/timer.c1734
8 files changed, 7400 insertions, 0 deletions
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 57a413fd0ebf..e59ce8b1b550 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,3 +1,4 @@
+obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
obj-y += timeconv.o posix-clock.o alarmtimer.o
@@ -12,3 +13,19 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
obj-$(CONFIG_TIMER_STATS) += timer_stats.o
obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
+
+$(obj)/time.o: $(obj)/timeconst.h
+
+quiet_cmd_hzfile = HZFILE $@
+ cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@
+
+targets += hz.bc
+$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE
+ $(call if_changed,hzfile)
+
+quiet_cmd_bc = BC $@
+ cmd_bc = bc -q $(filter-out FORCE,$^) > $@
+
+targets += timeconst.h
+$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
+ $(call if_changed,bc)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
new file mode 100644
index 000000000000..3ab28993f6e0
--- /dev/null
+++ b/kernel/time/hrtimer.c
@@ -0,0 +1,1915 @@
+/*
+ * linux/kernel/hrtimer.c
+ *
+ * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
+ * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
+ *
+ * High-resolution kernel timers
+ *
+ * In contrast to the low-resolution timeout API implemented in
+ * kernel/timer.c, hrtimers provide finer resolution and accuracy
+ * depending on system configuration and capabilities.
+ *
+ * These timers are currently used for:
+ * - itimers
+ * - POSIX timers
+ * - nanosleep
+ * - precise in-kernel timing
+ *
+ * Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * Credits:
+ * based on kernel/timer.c
+ *
+ * Help, testing, suggestions, bugfixes, improvements were
+ * provided by:
+ *
+ * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel
+ * et. al.
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/cpu.h>
+#include <linux/export.h>
+#include <linux/percpu.h>
+#include <linux/hrtimer.h>
+#include <linux/notifier.h>
+#include <linux/syscalls.h>
+#include <linux/kallsyms.h>
+#include <linux/interrupt.h>
+#include <linux/tick.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
+#include <linux/debugobjects.h>
+#include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
+#include <linux/timer.h>
+#include <linux/freezer.h>
+
+#include <asm/uaccess.h>
+
+#include <trace/events/timer.h>
+
+/*
+ * The timer bases:
+ *
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
+ */
+DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
+{
+
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
+ .clock_base =
+ {
+ {
+ .index = HRTIMER_BASE_MONOTONIC,
+ .clockid = CLOCK_MONOTONIC,
+ .get_time = &ktime_get,
+ .resolution = KTIME_LOW_RES,
+ },
+ {
+ .index = HRTIMER_BASE_REALTIME,
+ .clockid = CLOCK_REALTIME,
+ .get_time = &ktime_get_real,
+ .resolution = KTIME_LOW_RES,
+ },
+ {
+ .index = HRTIMER_BASE_BOOTTIME,
+ .clockid = CLOCK_BOOTTIME,
+ .get_time = &ktime_get_boottime,
+ .resolution = KTIME_LOW_RES,
+ },
+ {
+ .index = HRTIMER_BASE_TAI,
+ .clockid = CLOCK_TAI,
+ .get_time = &ktime_get_clocktai,
+ .resolution = KTIME_LOW_RES,
+ },
+ }
+};
+
+static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+ [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME,
+ [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC,
+ [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME,
+ [CLOCK_TAI] = HRTIMER_BASE_TAI,
+};
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+ return hrtimer_clock_to_base_table[clock_id];
+}
+
+
+/*
+ * Get the coarse grained time at the softirq based on xtime and
+ * wall_to_monotonic.
+ */
+static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
+{
+ ktime_t xtim, mono, boot;
+ struct timespec xts, tom, slp;
+ s32 tai_offset;
+
+ get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp);
+ tai_offset = timekeeping_get_tai_offset();
+
+ xtim = timespec_to_ktime(xts);
+ mono = ktime_add(xtim, timespec_to_ktime(tom));
+ boot = ktime_add(mono, timespec_to_ktime(slp));
+ base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+ base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
+ base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot;
+ base->clock_base[HRTIMER_BASE_TAI].softirq_time =
+ ktime_add(xtim, ktime_set(tai_offset, 0));
+}
+
+/*
+ * Functions and macros which are different for UP/SMP systems are kept in a
+ * single place
+ */
+#ifdef CONFIG_SMP
+
+/*
+ * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
+ * means that all timers which are tied to this base via timer->base are
+ * locked, and the base itself is locked too.
+ *
+ * So __run_timers/migrate_timers can safely modify all timers which could
+ * be found on the lists/queues.
+ *
+ * When the timer's base is locked, and the timer removed from list, it is
+ * possible to set timer->base = NULL and drop the lock: the timer remains
+ * locked.
+ */
+static
+struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
+ unsigned long *flags)
+{
+ struct hrtimer_clock_base *base;
+
+ for (;;) {
+ base = timer->base;
+ if (likely(base != NULL)) {
+ raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
+ if (likely(base == timer->base))
+ return base;
+ /* The timer has migrated to another CPU: */
+ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags);
+ }
+ cpu_relax();
+ }
+}
+
+/*
+ * With HIGHRES=y we do not migrate the timer when it is expiring
+ * before the next event on the target cpu because we cannot reprogram
+ * the target cpu hardware and we would cause it to fire late.
+ *
+ * Called with cpu_base->lock of target cpu held.
+ */
+static int
+hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+ ktime_t expires;
+
+ if (!new_base->cpu_base->hres_active)
+ return 0;
+
+ expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
+ return expires.tv64 <= new_base->cpu_base->expires_next.tv64;
+#else
+ return 0;
+#endif
+}
+
+/*
+ * Switch the timer base to the current CPU when possible.
+ */
+static inline struct hrtimer_clock_base *
+switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
+ int pinned)
+{
+ struct hrtimer_clock_base *new_base;
+ struct hrtimer_cpu_base *new_cpu_base;
+ int this_cpu = smp_processor_id();
+ int cpu = get_nohz_timer_target(pinned);
+ int basenum = base->index;
+
+again:
+ new_cpu_base = &per_cpu(hrtimer_bases, cpu);
+ new_base = &new_cpu_base->clock_base[basenum];
+
+ if (base != new_base) {
+ /*
+ * We are trying to move timer to new_base.
+ * However we can't change timer's base while it is running,
+ * so we keep it on the same CPU. No hassle vs. reprogramming
+ * the event source in the high resolution case. The softirq
+ * code will take care of this when the timer function has
+ * completed. There is no conflict as we hold the lock until
+ * the timer is enqueued.
+ */
+ if (unlikely(hrtimer_callback_running(timer)))
+ return base;
+
+ /* See the comment in lock_timer_base() */
+ timer->base = NULL;
+ raw_spin_unlock(&base->cpu_base->lock);
+ raw_spin_lock(&new_base->cpu_base->lock);
+
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ raw_spin_unlock(&new_base->cpu_base->lock);
+ raw_spin_lock(&base->cpu_base->lock);
+ timer->base = base;
+ goto again;
+ }
+ timer->base = new_base;
+ } else {
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ goto again;
+ }
+ }
+ return new_base;
+}
+
+#else /* CONFIG_SMP */
+
+static inline struct hrtimer_clock_base *
+lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
+{
+ struct hrtimer_clock_base *base = timer->base;
+
+ raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
+
+ return base;
+}
+
+# define switch_hrtimer_base(t, b, p) (b)
+
+#endif /* !CONFIG_SMP */
+
+/*
+ * Functions for the union type storage format of ktime_t which are
+ * too large for inlining:
+ */
+#if BITS_PER_LONG < 64
+# ifndef CONFIG_KTIME_SCALAR
+/**
+ * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable
+ * @kt: addend
+ * @nsec: the scalar nsec value to add
+ *
+ * Returns the sum of kt and nsec in ktime_t format
+ */
+ktime_t ktime_add_ns(const ktime_t kt, u64 nsec)
+{
+ ktime_t tmp;
+
+ if (likely(nsec < NSEC_PER_SEC)) {
+ tmp.tv64 = nsec;
+ } else {
+ unsigned long rem = do_div(nsec, NSEC_PER_SEC);
+
+ /* Make sure nsec fits into long */
+ if (unlikely(nsec > KTIME_SEC_MAX))
+ return (ktime_t){ .tv64 = KTIME_MAX };
+
+ tmp = ktime_set((long)nsec, rem);
+ }
+
+ return ktime_add(kt, tmp);
+}
+
+EXPORT_SYMBOL_GPL(ktime_add_ns);
+
+/**
+ * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable
+ * @kt: minuend
+ * @nsec: the scalar nsec value to subtract
+ *
+ * Returns the subtraction of @nsec from @kt in ktime_t format
+ */
+ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec)
+{
+ ktime_t tmp;
+
+ if (likely(nsec < NSEC_PER_SEC)) {
+ tmp.tv64 = nsec;
+ } else {
+ unsigned long rem = do_div(nsec, NSEC_PER_SEC);
+
+ tmp = ktime_set((long)nsec, rem);
+ }
+
+ return ktime_sub(kt, tmp);
+}
+
+EXPORT_SYMBOL_GPL(ktime_sub_ns);
+# endif /* !CONFIG_KTIME_SCALAR */
+
+/*
+ * Divide a ktime value by a nanosecond value
+ */
+u64 ktime_divns(const ktime_t kt, s64 div)
+{
+ u64 dclc;
+ int sft = 0;
+
+ dclc = ktime_to_ns(kt);
+ /* Make sure the divisor is less than 2^32: */
+ while (div >> 32) {
+ sft++;
+ div >>= 1;
+ }
+ dclc >>= sft;
+ do_div(dclc, (unsigned long) div);
+
+ return dclc;
+}
+#endif /* BITS_PER_LONG >= 64 */
+
+/*
+ * Add two ktime values and do a safety check for overflow:
+ */
+ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
+{
+ ktime_t res = ktime_add(lhs, rhs);
+
+ /*
+ * We use KTIME_SEC_MAX here, the maximum timeout which we can
+ * return to user space in a timespec:
+ */
+ if (res.tv64 < 0 || res.tv64 < lhs.tv64 || res.tv64 < rhs.tv64)
+ res = ktime_set(KTIME_SEC_MAX, 0);
+
+ return res;
+}
+
+EXPORT_SYMBOL_GPL(ktime_add_safe);
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+
+static struct debug_obj_descr hrtimer_debug_descr;
+
+static void *hrtimer_debug_hint(void *addr)
+{
+ return ((struct hrtimer *) addr)->function;
+}
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int hrtimer_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct hrtimer *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ hrtimer_cancel(timer);
+ debug_object_init(timer, &hrtimer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int hrtimer_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int hrtimer_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct hrtimer *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ hrtimer_cancel(timer);
+ debug_object_free(timer, &hrtimer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr hrtimer_debug_descr = {
+ .name = "hrtimer",
+ .debug_hint = hrtimer_debug_hint,
+ .fixup_init = hrtimer_fixup_init,
+ .fixup_activate = hrtimer_fixup_activate,
+ .fixup_free = hrtimer_fixup_free,
+};
+
+static inline void debug_hrtimer_init(struct hrtimer *timer)
+{
+ debug_object_init(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_activate(struct hrtimer *timer)
+{
+ debug_object_activate(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_deactivate(struct hrtimer *timer)
+{
+ debug_object_deactivate(timer, &hrtimer_debug_descr);
+}
+
+static inline void debug_hrtimer_free(struct hrtimer *timer)
+{
+ debug_object_free(timer, &hrtimer_debug_descr);
+}
+
+static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode);
+
+void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
+{
+ debug_object_init_on_stack(timer, &hrtimer_debug_descr);
+ __hrtimer_init(timer, clock_id, mode);
+}
+EXPORT_SYMBOL_GPL(hrtimer_init_on_stack);
+
+void destroy_hrtimer_on_stack(struct hrtimer *timer)
+{
+ debug_object_free(timer, &hrtimer_debug_descr);
+}
+
+#else
+static inline void debug_hrtimer_init(struct hrtimer *timer) { }
+static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
+static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
+#endif
+
+static inline void
+debug_init(struct hrtimer *timer, clockid_t clockid,
+ enum hrtimer_mode mode)
+{
+ debug_hrtimer_init(timer);
+ trace_hrtimer_init(timer, clockid, mode);
+}
+
+static inline void debug_activate(struct hrtimer *timer)
+{
+ debug_hrtimer_activate(timer);
+ trace_hrtimer_start(timer);
+}
+
+static inline void debug_deactivate(struct hrtimer *timer)
+{
+ debug_hrtimer_deactivate(timer);
+ trace_hrtimer_cancel(timer);
+}
+
+/* High resolution timer related functions */
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer enabled ?
+ */
+static int hrtimer_hres_enabled __read_mostly = 1;
+
+/*
+ * Enable / Disable high resolution mode
+ */
+static int __init setup_hrtimer_hres(char *str)
+{
+ if (!strcmp(str, "off"))
+ hrtimer_hres_enabled = 0;
+ else if (!strcmp(str, "on"))
+ hrtimer_hres_enabled = 1;
+ else
+ return 0;
+ return 1;
+}
+
+__setup("highres=", setup_hrtimer_hres);
+
+/*
+ * hrtimer_high_res_enabled - query, if the highres mode is enabled
+ */
+static inline int hrtimer_is_hres_enabled(void)
+{
+ return hrtimer_hres_enabled;
+}
+
+/*
+ * Is the high resolution mode active ?
+ */
+static inline int hrtimer_hres_active(void)
+{
+ return __this_cpu_read(hrtimer_bases.hres_active);
+}
+
+/*
+ * Reprogram the event source with checking both queues for the
+ * next event
+ * Called with interrupts disabled and base->lock held
+ */
+static void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
+{
+ int i;
+ struct hrtimer_clock_base *base = cpu_base->clock_base;
+ ktime_t expires, expires_next;
+
+ expires_next.tv64 = KTIME_MAX;
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+ struct hrtimer *timer;
+ struct timerqueue_node *next;
+
+ next = timerqueue_getnext(&base->active);
+ if (!next)
+ continue;
+ timer = container_of(next, struct hrtimer, node);
+
+ expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+ /*
+ * clock_was_set() has changed base->offset so the
+ * result might be negative. Fix it up to prevent a
+ * false positive in clockevents_program_event()
+ */
+ if (expires.tv64 < 0)
+ expires.tv64 = 0;
+ if (expires.tv64 < expires_next.tv64)
+ expires_next = expires;
+ }
+
+ if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
+ return;
+
+ cpu_base->expires_next.tv64 = expires_next.tv64;
+
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * leave the hang delay active in the hardware. We want the
+ * system to make progress. That also prevents the following
+ * scenario:
+ * T1 expires 50ms from now
+ * T2 expires 5s from now
+ *
+ * T1 is removed, so this code is called and would reprogram
+ * the hardware to 5s from now. Any hrtimer_start after that
+ * will not reprogram the hardware due to hang_detected being
+ * set. So we'd effectivly block all timers until the T2 event
+ * fires.
+ */
+ if (cpu_base->hang_detected)
+ return;
+
+ if (cpu_base->expires_next.tv64 != KTIME_MAX)
+ tick_program_event(cpu_base->expires_next, 1);
+}
+
+/*
+ * Shared reprogramming for clock_realtime and clock_monotonic
+ *
+ * When a timer is enqueued and expires earlier than the already enqueued
+ * timers, we have to check, whether it expires earlier than the timer for
+ * which the clock event device was armed.
+ *
+ * Called with interrupts disabled and base->cpu_base.lock held
+ */
+static int hrtimer_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+ int res;
+
+ WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0);
+
+ /*
+ * When the callback is running, we do not reprogram the clock event
+ * device. The timer callback is either running on a different CPU or
+ * the callback is executed in the hrtimer_interrupt context. The
+ * reprogramming is handled either by the softirq, which called the
+ * callback or at the end of the hrtimer_interrupt.
+ */
+ if (hrtimer_callback_running(timer))
+ return 0;
+
+ /*
+ * CLOCK_REALTIME timer might be requested with an absolute
+ * expiry time which is less than base->offset. Nothing wrong
+ * about that, just avoid to call into the tick code, which
+ * has now objections against negative expiry values.
+ */
+ if (expires.tv64 < 0)
+ return -ETIME;
+
+ if (expires.tv64 >= cpu_base->expires_next.tv64)
+ return 0;
+
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * do not schedule a timer which is earlier than the expiry
+ * which we enforced in the hang detection. We want the system
+ * to make progress.
+ */
+ if (cpu_base->hang_detected)
+ return 0;
+
+ /*
+ * Clockevents returns -ETIME, when the event was in the past.
+ */
+ res = tick_program_event(expires, 0);
+ if (!IS_ERR_VALUE(res))
+ cpu_base->expires_next = expires;
+ return res;
+}
+
+/*
+ * Initialize the high resolution related parts of cpu_base
+ */
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
+{
+ base->expires_next.tv64 = KTIME_MAX;
+ base->hres_active = 0;
+}
+
+/*
+ * When High resolution timers are active, try to reprogram. Note, that in case
+ * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
+ * check happens. The timer gets enqueued into the rbtree. The reprogramming
+ * and expiry check is done in the hrtimer_interrupt or in the softirq.
+ */
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ return base->cpu_base->hres_active && hrtimer_reprogram(timer, base);
+}
+
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+ ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+ ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset;
+
+ return ktime_get_update_offsets(offs_real, offs_boot, offs_tai);
+}
+
+/*
+ * Retrigger next event is called after clock was set
+ *
+ * Called with interrupts disabled via on_each_cpu()
+ */
+static void retrigger_next_event(void *arg)
+{
+ struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+
+ if (!hrtimer_hres_active())
+ return;
+
+ raw_spin_lock(&base->lock);
+ hrtimer_update_base(base);
+ hrtimer_force_reprogram(base, 0);
+ raw_spin_unlock(&base->lock);
+}
+
+/*
+ * Switch to high resolution mode
+ */
+static int hrtimer_switch_to_hres(void)
+{
+ int i, cpu = smp_processor_id();
+ struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu);
+ unsigned long flags;
+
+ if (base->hres_active)
+ return 1;
+
+ local_irq_save(flags);
+
+ if (tick_init_highres()) {
+ local_irq_restore(flags);
+ printk(KERN_WARNING "Could not switch to high resolution "
+ "mode on CPU %d\n", cpu);
+ return 0;
+ }
+ base->hres_active = 1;
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
+ base->clock_base[i].resolution = KTIME_HIGH_RES;
+
+ tick_setup_sched_timer();
+ /* "Retrigger" the interrupt to get things going */
+ retrigger_next_event(NULL);
+ local_irq_restore(flags);
+ return 1;
+}
+
+static void clock_was_set_work(struct work_struct *work)
+{
+ clock_was_set();
+}
+
+static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+
+/*
+ * Called from timekeeping and resume code to reprogramm the hrtimer
+ * interrupt device on all cpus.
+ */
+void clock_was_set_delayed(void)
+{
+ schedule_work(&hrtimer_work);
+}
+
+#else
+
+static inline int hrtimer_hres_active(void) { return 0; }
+static inline int hrtimer_is_hres_enabled(void) { return 0; }
+static inline int hrtimer_switch_to_hres(void) { return 0; }
+static inline void
+hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
+static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ return 0;
+}
+static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
+static inline void retrigger_next_event(void *arg) { }
+
+#endif /* CONFIG_HIGH_RES_TIMERS */
+
+/*
+ * Clock realtime was set
+ *
+ * Change the offset of the realtime clock vs. the monotonic
+ * clock.
+ *
+ * We might have to reprogram the high resolution timer interrupt. On
+ * SMP we call the architecture specific code to retrigger _all_ high
+ * resolution timer interrupts. On UP we just disable interrupts and
+ * call the high resolution interrupt code.
+ */
+void clock_was_set(void)
+{
+#ifdef CONFIG_HIGH_RES_TIMERS
+ /* Retrigger the CPU local events everywhere */
+ on_each_cpu(retrigger_next_event, NULL, 1);
+#endif
+ timerfd_clock_was_set();
+}
+
+/*
+ * During resume we might have to reprogram the high resolution timer
+ * interrupt on all online CPUs. However, all other CPUs will be
+ * stopped with IRQs interrupts disabled so the clock_was_set() call
+ * must be deferred.
+ */
+void hrtimers_resume(void)
+{
+ WARN_ONCE(!irqs_disabled(),
+ KERN_INFO "hrtimers_resume() called with IRQs enabled!");
+
+ /* Retrigger on the local CPU */
+ retrigger_next_event(NULL);
+ /* And schedule a retrigger for all others */
+ clock_was_set_delayed();
+}
+
+static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ if (timer->start_site)
+ return;
+ timer->start_site = __builtin_return_address(0);
+ memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+ timer->start_pid = current->pid;
+#endif
+}
+
+static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ timer->start_site = NULL;
+#endif
+}
+
+static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
+{
+#ifdef CONFIG_TIMER_STATS
+ if (likely(!timer_stats_active))
+ return;
+ timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+ timer->function, timer->start_comm, 0);
+#endif
+}
+
+/*
+ * Counterpart to lock_hrtimer_base above:
+ */
+static inline
+void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
+{
+ raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags);
+}
+
+/**
+ * hrtimer_forward - forward the timer expiry
+ * @timer: hrtimer to forward
+ * @now: forward past this time
+ * @interval: the interval to forward
+ *
+ * Forward the timer expiry so it will expire in the future.
+ * Returns the number of overruns.
+ */
+u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval)
+{
+ u64 orun = 1;
+ ktime_t delta;
+
+ delta = ktime_sub(now, hrtimer_get_expires(timer));
+
+ if (delta.tv64 < 0)
+ return 0;
+
+ if (interval.tv64 < timer->base->resolution.tv64)
+ interval.tv64 = timer->base->resolution.tv64;
+
+ if (unlikely(delta.tv64 >= interval.tv64)) {
+ s64 incr = ktime_to_ns(interval);
+
+ orun = ktime_divns(delta, incr);
+ hrtimer_add_expires_ns(timer, incr * orun);
+ if (hrtimer_get_expires_tv64(timer) > now.tv64)
+ return orun;
+ /*
+ * This (and the ktime_add() below) is the
+ * correction for exact:
+ */
+ orun++;
+ }
+ hrtimer_add_expires(timer, interval);
+
+ return orun;
+}
+EXPORT_SYMBOL_GPL(hrtimer_forward);
+
+/*
+ * enqueue_hrtimer - internal function to (re)start a timer
+ *
+ * The timer is inserted in expiry order. Insertion into the
+ * red black tree is O(log(n)). Must hold the base lock.
+ *
+ * Returns 1 when the new timer is the leftmost timer in the tree.
+ */
+static int enqueue_hrtimer(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ debug_activate(timer);
+
+ timerqueue_add(&base->active, &timer->node);
+ base->cpu_base->active_bases |= 1 << base->index;
+
+ /*
+ * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the
+ * state of a possibly running callback.
+ */
+ timer->state |= HRTIMER_STATE_ENQUEUED;
+
+ return (&timer->node == base->active.next);
+}
+
+/*
+ * __remove_hrtimer - internal function to remove a timer
+ *
+ * Caller must hold the base lock.
+ *
+ * High resolution timer mode reprograms the clock event device when the
+ * timer is the one which expires next. The caller can disable this by setting
+ * reprogram to zero. This is useful, when the context does a reprogramming
+ * anyway (e.g. timer interrupt)
+ */
+static void __remove_hrtimer(struct hrtimer *timer,
+ struct hrtimer_clock_base *base,
+ unsigned long newstate, int reprogram)
+{
+ struct timerqueue_node *next_timer;
+ if (!(timer->state & HRTIMER_STATE_ENQUEUED))
+ goto out;
+
+ next_timer = timerqueue_getnext(&base->active);
+ timerqueue_del(&base->active, &timer->node);
+ if (&timer->node == next_timer) {
+#ifdef CONFIG_HIGH_RES_TIMERS
+ /* Reprogram the clock event device. if enabled */
+ if (reprogram && hrtimer_hres_active()) {
+ ktime_t expires;
+
+ expires = ktime_sub(hrtimer_get_expires(timer),
+ base->offset);
+ if (base->cpu_base->expires_next.tv64 == expires.tv64)
+ hrtimer_force_reprogram(base->cpu_base, 1);
+ }
+#endif
+ }
+ if (!timerqueue_getnext(&base->active))
+ base->cpu_base->active_bases &= ~(1 << base->index);
+out:
+ timer->state = newstate;
+}
+
+/*
+ * remove hrtimer, called with base lock held
+ */
+static inline int
+remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
+{
+ if (hrtimer_is_queued(timer)) {
+ unsigned long state;
+ int reprogram;
+
+ /*
+ * Remove the timer and force reprogramming when high
+ * resolution mode is active and the timer is on the current
+ * CPU. If we remove a timer on another CPU, reprogramming is
+ * skipped. The interrupt event on this CPU is fired and
+ * reprogramming happens in the interrupt handler. This is a
+ * rare case and less expensive than a smp call.
+ */
+ debug_deactivate(timer);
+ timer_stats_hrtimer_clear_start_info(timer);
+ reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+ /*
+ * We must preserve the CALLBACK state flag here,
+ * otherwise we could move the timer base in
+ * switch_hrtimer_base.
+ */
+ state = timer->state & HRTIMER_STATE_CALLBACK;
+ __remove_hrtimer(timer, base, state, reprogram);
+ return 1;
+ }
+ return 0;
+}
+
+int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode,
+ int wakeup)
+{
+ struct hrtimer_clock_base *base, *new_base;
+ unsigned long flags;
+ int ret, leftmost;
+
+ base = lock_hrtimer_base(timer, &flags);
+
+ /* Remove an active timer from the queue: */
+ ret = remove_hrtimer(timer, base);
+
+ if (mode & HRTIMER_MODE_REL) {
+ tim = ktime_add_safe(tim, base->get_time());
+ /*
+ * CONFIG_TIME_LOW_RES is a temporary way for architectures
+ * to signal that they simply return xtime in
+ * do_gettimeoffset(). In this case we want to round up by
+ * resolution when starting a relative timer, to avoid short
+ * timeouts. This will go away with the GTOD framework.
+ */
+#ifdef CONFIG_TIME_LOW_RES
+ tim = ktime_add_safe(tim, base->resolution);
+#endif
+ }
+
+ hrtimer_set_expires_range_ns(timer, tim, delta_ns);
+
+ /* Switch the timer base, if necessary: */
+ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
+ timer_stats_hrtimer_set_start_info(timer);
+
+ leftmost = enqueue_hrtimer(timer, new_base);
+
+ /*
+ * Only allow reprogramming if the new base is on this CPU.
+ * (it might still be on another CPU if the timer was pending)
+ *
+ * XXX send_remote_softirq() ?
+ */
+ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
+ && hrtimer_enqueue_reprogram(timer, new_base)) {
+ if (wakeup) {
+ /*
+ * We need to drop cpu_base->lock to avoid a
+ * lock ordering issue vs. rq->lock.
+ */
+ raw_spin_unlock(&new_base->cpu_base->lock);
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ local_irq_restore(flags);
+ return ret;
+ } else {
+ __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ }
+ }
+
+ unlock_hrtimer_base(timer, &flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @delta_ns: "slack" range for the timer
+ * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL)
+ *
+ * Returns:
+ * 0 on success
+ * 1 when the timer was active
+ */
+int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+ unsigned long delta_ns, const enum hrtimer_mode mode)
+{
+ return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1);
+}
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an hrtimer on the current CPU
+ * @timer: the timer to be added
+ * @tim: expiry time
+ * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL)
+ *
+ * Returns:
+ * 0 on success
+ * 1 when the timer was active
+ */
+int
+hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+{
+ return __hrtimer_start_range_ns(timer, tim, 0, mode, 1);
+}
+EXPORT_SYMBOL_GPL(hrtimer_start);
+
+
+/**
+ * hrtimer_try_to_cancel - try to deactivate a timer
+ * @timer: hrtimer to stop
+ *
+ * Returns:
+ * 0 when the timer was not active
+ * 1 when the timer was active
+ * -1 when the timer is currently excuting the callback function and
+ * cannot be stopped
+ */
+int hrtimer_try_to_cancel(struct hrtimer *timer)
+{
+ struct hrtimer_clock_base *base;
+ unsigned long flags;
+ int ret = -1;
+
+ base = lock_hrtimer_base(timer, &flags);
+
+ if (!hrtimer_callback_running(timer))
+ ret = remove_hrtimer(timer, base);
+
+ unlock_hrtimer_base(timer, &flags);
+
+ return ret;
+
+}
+EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);
+
+/**
+ * hrtimer_cancel - cancel a timer and wait for the handler to finish.
+ * @timer: the timer to be cancelled
+ *
+ * Returns:
+ * 0 when the timer was not active
+ * 1 when the timer was active
+ */
+int hrtimer_cancel(struct hrtimer *timer)
+{
+ for (;;) {
+ int ret = hrtimer_try_to_cancel(timer);
+
+ if (ret >= 0)
+ return ret;
+ cpu_relax();
+ }
+}
+EXPORT_SYMBOL_GPL(hrtimer_cancel);
+
+/**
+ * hrtimer_get_remaining - get remaining time for the timer
+ * @timer: the timer to read
+ */
+ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
+{
+ unsigned long flags;
+ ktime_t rem;
+
+ lock_hrtimer_base(timer, &flags);
+ rem = hrtimer_expires_remaining(timer);
+ unlock_hrtimer_base(timer, &flags);
+
+ return rem;
+}
+EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
+
+#ifdef CONFIG_NO_HZ_COMMON
+/**
+ * hrtimer_get_next_event - get the time until next expiry event
+ *
+ * Returns the delta to the next expiry event or KTIME_MAX if no timer
+ * is pending.
+ */
+ktime_t hrtimer_get_next_event(void)
+{
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ struct hrtimer_clock_base *base = cpu_base->clock_base;
+ ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+ unsigned long flags;
+ int i;
+
+ raw_spin_lock_irqsave(&cpu_base->lock, flags);
+
+ if (!hrtimer_hres_active()) {
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+ struct hrtimer *timer;
+ struct timerqueue_node *next;
+
+ next = timerqueue_getnext(&base->active);
+ if (!next)
+ continue;
+
+ timer = container_of(next, struct hrtimer, node);
+ delta.tv64 = hrtimer_get_expires_tv64(timer);
+ delta = ktime_sub(delta, base->get_time());
+ if (delta.tv64 < mindelta.tv64)
+ mindelta.tv64 = delta.tv64;
+ }
+ }
+
+ raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
+
+ if (mindelta.tv64 < 0)
+ mindelta.tv64 = 0;
+ return mindelta;
+}
+#endif
+
+static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
+{
+ struct hrtimer_cpu_base *cpu_base;
+ int base;
+
+ memset(timer, 0, sizeof(struct hrtimer));
+
+ cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+
+ if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
+ clock_id = CLOCK_MONOTONIC;
+
+ base = hrtimer_clockid_to_base(clock_id);
+ timer->base = &cpu_base->clock_base[base];
+ timerqueue_init(&timer->node);
+
+#ifdef CONFIG_TIMER_STATS
+ timer->start_site = NULL;
+ timer->start_pid = -1;
+ memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
+}
+
+/**
+ * hrtimer_init - initialize a timer to the given clock
+ * @timer: the timer to be initialized
+ * @clock_id: the clock to be used
+ * @mode: timer mode abs/rel
+ */
+void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
+ enum hrtimer_mode mode)
+{
+ debug_init(timer, clock_id, mode);
+ __hrtimer_init(timer, clock_id, mode);
+}
+EXPORT_SYMBOL_GPL(hrtimer_init);
+
+/**
+ * hrtimer_get_res - get the timer resolution for a clock
+ * @which_clock: which clock to query
+ * @tp: pointer to timespec variable to store the resolution
+ *
+ * Store the resolution of the clock selected by @which_clock in the
+ * variable pointed to by @tp.
+ */
+int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
+{
+ struct hrtimer_cpu_base *cpu_base;
+ int base = hrtimer_clockid_to_base(which_clock);
+
+ cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+ *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(hrtimer_get_res);
+
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
+{
+ struct hrtimer_clock_base *base = timer->base;
+ struct hrtimer_cpu_base *cpu_base = base->cpu_base;
+ enum hrtimer_restart (*fn)(struct hrtimer *);
+ int restart;
+
+ WARN_ON(!irqs_disabled());
+
+ debug_deactivate(timer);
+ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+ timer_stats_account_hrtimer(timer);
+ fn = timer->function;
+
+ /*
+ * Because we run timers from hardirq context, there is no chance
+ * they get migrated to another cpu, therefore its safe to unlock
+ * the timer base.
+ */
+ raw_spin_unlock(&cpu_base->lock);
+ trace_hrtimer_expire_entry(timer, now);
+ restart = fn(timer);
+ trace_hrtimer_expire_exit(timer);
+ raw_spin_lock(&cpu_base->lock);
+
+ /*
+ * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+ * we do not reprogramm the event hardware. Happens either in
+ * hrtimer_start_range_ns() or in hrtimer_interrupt()
+ */
+ if (restart != HRTIMER_NORESTART) {
+ BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
+ enqueue_hrtimer(timer, base);
+ }
+
+ WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+
+ timer->state &= ~HRTIMER_STATE_CALLBACK;
+}
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
+/*
+ * High resolution timer interrupt
+ * Called with interrupts disabled
+ */
+void hrtimer_interrupt(struct clock_event_device *dev)
+{
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ ktime_t expires_next, now, entry_time, delta;
+ int i, retries = 0;
+
+ BUG_ON(!cpu_base->hres_active);
+ cpu_base->nr_events++;
+ dev->next_event.tv64 = KTIME_MAX;
+
+ raw_spin_lock(&cpu_base->lock);
+ entry_time = now = hrtimer_update_base(cpu_base);
+retry:
+ expires_next.tv64 = KTIME_MAX;
+ /*
+ * We set expires_next to KTIME_MAX here with cpu_base->lock
+ * held to prevent that a timer is enqueued in our queue via
+ * the migration code. This does not affect enqueueing of
+ * timers which run their callback and need to be requeued on
+ * this CPU.
+ */
+ cpu_base->expires_next.tv64 = KTIME_MAX;
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+ struct hrtimer_clock_base *base;
+ struct timerqueue_node *node;
+ ktime_t basenow;
+
+ if (!(cpu_base->active_bases & (1 << i)))
+ continue;
+
+ base = cpu_base->clock_base + i;
+ basenow = ktime_add(now, base->offset);
+
+ while ((node = timerqueue_getnext(&base->active))) {
+ struct hrtimer *timer;
+
+ timer = container_of(node, struct hrtimer, node);
+
+ /*
+ * The immediate goal for using the softexpires is
+ * minimizing wakeups, not running timers at the
+ * earliest interrupt after their soft expiration.
+ * This allows us to avoid using a Priority Search
+ * Tree, which can answer a stabbing querry for
+ * overlapping intervals and instead use the simple
+ * BST we already have.
+ * We don't add extra wakeups by delaying timers that
+ * are right-of a not yet expired timer, because that
+ * timer will have to trigger a wakeup anyway.
+ */
+
+ if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
+ ktime_t expires;
+
+ expires = ktime_sub(hrtimer_get_expires(timer),
+ base->offset);
+ if (expires.tv64 < 0)
+ expires.tv64 = KTIME_MAX;
+ if (expires.tv64 < expires_next.tv64)
+ expires_next = expires;
+ break;
+ }
+
+ __run_hrtimer(timer, &basenow);
+ }
+ }
+
+ /*
+ * Store the new expiry value so the migration code can verify
+ * against it.
+ */
+ cpu_base->expires_next = expires_next;
+ raw_spin_unlock(&cpu_base->lock);
+
+ /* Reprogramming necessary ? */
+ if (expires_next.tv64 == KTIME_MAX ||
+ !tick_program_event(expires_next, 0)) {
+ cpu_base->hang_detected = 0;
+ return;
+ }
+
+ /*
+ * The next timer was already expired due to:
+ * - tracing
+ * - long lasting callbacks
+ * - being scheduled away when running in a VM
+ *
+ * We need to prevent that we loop forever in the hrtimer
+ * interrupt routine. We give it 3 attempts to avoid
+ * overreacting on some spurious event.
+ *
+ * Acquire base lock for updating the offsets and retrieving
+ * the current time.
+ */
+ raw_spin_lock(&cpu_base->lock);
+ now = hrtimer_update_base(cpu_base);
+ cpu_base->nr_retries++;
+ if (++retries < 3)
+ goto retry;
+ /*
+ * Give the system a chance to do something else than looping
+ * here. We stored the entry time, so we know exactly how long
+ * we spent here. We schedule the next event this amount of
+ * time away.
+ */
+ cpu_base->nr_hangs++;
+ cpu_base->hang_detected = 1;
+ raw_spin_unlock(&cpu_base->lock);
+ delta = ktime_sub(now, entry_time);
+ if (delta.tv64 > cpu_base->max_hang_time.tv64)
+ cpu_base->max_hang_time = delta;
+ /*
+ * Limit it to a sensible value as we enforce a longer
+ * delay. Give the CPU at least 100ms to catch up.
+ */
+ if (delta.tv64 > 100 * NSEC_PER_MSEC)
+ expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
+ else
+ expires_next = ktime_add(now, delta);
+ tick_program_event(expires_next, 1);
+ printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
+ ktime_to_ns(delta));
+}
+
+/*
+ * local version of hrtimer_peek_ahead_timers() called with interrupts
+ * disabled.
+ */
+static void __hrtimer_peek_ahead_timers(void)
+{
+ struct tick_device *td;
+
+ if (!hrtimer_hres_active())
+ return;
+
+ td = &__get_cpu_var(tick_cpu_device);
+ if (td && td->evtdev)
+ hrtimer_interrupt(td->evtdev);
+}
+
+/**
+ * hrtimer_peek_ahead_timers -- run soft-expired timers now
+ *
+ * hrtimer_peek_ahead_timers will peek at the timer queue of
+ * the current cpu and check if there are any timers for which
+ * the soft expires time has passed. If any such timers exist,
+ * they are run immediately and then removed from the timer queue.
+ *
+ */
+void hrtimer_peek_ahead_timers(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __hrtimer_peek_ahead_timers();
+ local_irq_restore(flags);
+}
+
+static void run_hrtimer_softirq(struct softirq_action *h)
+{
+ hrtimer_peek_ahead_timers();
+}
+
+#else /* CONFIG_HIGH_RES_TIMERS */
+
+static inline void __hrtimer_peek_ahead_timers(void) { }
+
+#endif /* !CONFIG_HIGH_RES_TIMERS */
+
+/*
+ * Called from timer softirq every jiffy, expire hrtimers:
+ *
+ * For HRT its the fall back code to run the softirq in the timer
+ * softirq context in case the hrtimer initialization failed or has
+ * not been done yet.
+ */
+void hrtimer_run_pending(void)
+{
+ if (hrtimer_hres_active())
+ return;
+
+ /*
+ * This _is_ ugly: We have to check in the softirq context,
+ * whether we can switch to highres and / or nohz mode. The
+ * clocksource switch happens in the timer interrupt with
+ * xtime_lock held. Notification from there only sets the
+ * check bit in the tick_oneshot code, otherwise we might
+ * deadlock vs. xtime_lock.
+ */
+ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
+ hrtimer_switch_to_hres();
+}
+
+/*
+ * Called from hardirq context every jiffy
+ */
+void hrtimer_run_queues(void)
+{
+ struct timerqueue_node *node;
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ struct hrtimer_clock_base *base;
+ int index, gettime = 1;
+
+ if (hrtimer_hres_active())
+ return;
+
+ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+ base = &cpu_base->clock_base[index];
+ if (!timerqueue_getnext(&base->active))
+ continue;
+
+ if (gettime) {
+ hrtimer_get_softirq_time(cpu_base);
+ gettime = 0;
+ }
+
+ raw_spin_lock(&cpu_base->lock);
+
+ while ((node = timerqueue_getnext(&base->active))) {
+ struct hrtimer *timer;
+
+ timer = container_of(node, struct hrtimer, node);
+ if (base->softirq_time.tv64 <=
+ hrtimer_get_expires_tv64(timer))
+ break;
+
+ __run_hrtimer(timer, &base->softirq_time);
+ }
+ raw_spin_unlock(&cpu_base->lock);
+ }
+}
+
+/*
+ * Sleep related functions:
+ */
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
+{
+ struct hrtimer_sleeper *t =
+ container_of(timer, struct hrtimer_sleeper, timer);
+ struct task_struct *task = t->task;
+
+ t->task = NULL;
+ if (task)
+ wake_up_process(task);
+
+ return HRTIMER_NORESTART;
+}
+
+void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
+{
+ sl->timer.function = hrtimer_wakeup;
+ sl->task = task;
+}
+EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
+
+static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
+{
+ hrtimer_init_sleeper(t, current);
+
+ do {
+ set_current_state(TASK_INTERRUPTIBLE);
+ hrtimer_start_expires(&t->timer, mode);
+ if (!hrtimer_active(&t->timer))
+ t->task = NULL;
+
+ if (likely(t->task))
+ freezable_schedule();
+
+ hrtimer_cancel(&t->timer);
+ mode = HRTIMER_MODE_ABS;
+
+ } while (t->task && !signal_pending(current));
+
+ __set_current_state(TASK_RUNNING);
+
+ return t->task == NULL;
+}
+
+static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp)
+{
+ struct timespec rmt;
+ ktime_t rem;
+
+ rem = hrtimer_expires_remaining(timer);
+ if (rem.tv64 <= 0)
+ return 0;
+ rmt = ktime_to_timespec(rem);
+
+ if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
+ return -EFAULT;
+
+ return 1;
+}
+
+long __sched hrtimer_nanosleep_restart(struct restart_block *restart)
+{
+ struct hrtimer_sleeper t;
+ struct timespec __user *rmtp;
+ int ret = 0;
+
+ hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid,
+ HRTIMER_MODE_ABS);
+ hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
+
+ if (do_nanosleep(&t, HRTIMER_MODE_ABS))
+ goto out;
+
+ rmtp = restart->nanosleep.rmtp;
+ if (rmtp) {
+ ret = update_rmtp(&t.timer, rmtp);
+ if (ret <= 0)
+ goto out;
+ }
+
+ /* The other values in restart are already filled in */
+ ret = -ERESTART_RESTARTBLOCK;
+out:
+ destroy_hrtimer_on_stack(&t.timer);
+ return ret;
+}
+
+long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
+ const enum hrtimer_mode mode, const clockid_t clockid)
+{
+ struct restart_block *restart;
+ struct hrtimer_sleeper t;
+ int ret = 0;
+ unsigned long slack;
+
+ slack = current->timer_slack_ns;
+ if (dl_task(current) || rt_task(current))
+ slack = 0;
+
+ hrtimer_init_on_stack(&t.timer, clockid, mode);
+ hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
+ if (do_nanosleep(&t, mode))
+ goto out;
+
+ /* Absolute timers do not update the rmtp value and restart: */
+ if (mode == HRTIMER_MODE_ABS) {
+ ret = -ERESTARTNOHAND;
+ goto out;
+ }
+
+ if (rmtp) {
+ ret = update_rmtp(&t.timer, rmtp);
+ if (ret <= 0)
+ goto out;
+ }
+
+ restart = &current_thread_info()->restart_block;
+ restart->fn = hrtimer_nanosleep_restart;
+ restart->nanosleep.clockid = t.timer.base->clockid;
+ restart->nanosleep.rmtp = rmtp;
+ restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+
+ ret = -ERESTART_RESTARTBLOCK;
+out:
+ destroy_hrtimer_on_stack(&t.timer);
+ return ret;
+}
+
+SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
+ struct timespec __user *, rmtp)
+{
+ struct timespec tu;
+
+ if (copy_from_user(&tu, rqtp, sizeof(tu)))
+ return -EFAULT;
+
+ if (!timespec_valid(&tu))
+ return -EINVAL;
+
+ return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+}
+
+/*
+ * Functions related to boot-time initialization:
+ */
+static void init_hrtimers_cpu(int cpu)
+{
+ struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
+ int i;
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+ cpu_base->clock_base[i].cpu_base = cpu_base;
+ timerqueue_init_head(&cpu_base->clock_base[i].active);
+ }
+
+ hrtimer_init_hres(cpu_base);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+ struct hrtimer_clock_base *new_base)
+{
+ struct hrtimer *timer;
+ struct timerqueue_node *node;
+
+ while ((node = timerqueue_getnext(&old_base->active))) {
+ timer = container_of(node, struct hrtimer, node);
+ BUG_ON(hrtimer_callback_running(timer));
+ debug_deactivate(timer);
+
+ /*
+ * Mark it as STATE_MIGRATE not INACTIVE otherwise the
+ * timer could be seen as !active and just vanish away
+ * under us on another CPU
+ */
+ __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
+ timer->base = new_base;
+ /*
+ * Enqueue the timers on the new cpu. This does not
+ * reprogram the event device in case the timer
+ * expires before the earliest on this CPU, but we run
+ * hrtimer_interrupt after we migrated everything to
+ * sort out already expired timers and reprogram the
+ * event device.
+ */
+ enqueue_hrtimer(timer, new_base);
+
+ /* Clear the migration state bit */
+ timer->state &= ~HRTIMER_STATE_MIGRATE;
+ }
+}
+
+static void migrate_hrtimers(int scpu)
+{
+ struct hrtimer_cpu_base *old_base, *new_base;
+ int i;
+
+ BUG_ON(cpu_online(scpu));
+ tick_cancel_sched_timer(scpu);
+
+ local_irq_disable();
+ old_base = &per_cpu(hrtimer_bases, scpu);
+ new_base = &__get_cpu_var(hrtimer_bases);
+ /*
+ * The caller is globally serialized and nobody else
+ * takes two locks at once, deadlock is not possible.
+ */
+ raw_spin_lock(&new_base->lock);
+ raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
+
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+ migrate_hrtimer_list(&old_base->clock_base[i],
+ &new_base->clock_base[i]);
+ }
+
+ raw_spin_unlock(&old_base->lock);
+ raw_spin_unlock(&new_base->lock);
+
+ /* Check, if we got expired work to do */
+ __hrtimer_peek_ahead_timers();
+ local_irq_enable();
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int hrtimer_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ int scpu = (long)hcpu;
+
+ switch (action) {
+
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ init_hrtimers_cpu(scpu);
+ break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DYING, &scpu);
+ break;
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ {
+ clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
+ migrate_hrtimers(scpu);
+ break;
+ }
+#endif
+
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block hrtimers_nb = {
+ .notifier_call = hrtimer_cpu_notify,
+};
+
+void __init hrtimers_init(void)
+{
+ hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
+ (void *)(long)smp_processor_id());
+ register_cpu_notifier(&hrtimers_nb);
+#ifdef CONFIG_HIGH_RES_TIMERS
+ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
+#endif
+}
+
+/**
+ * schedule_hrtimeout_range_clock - sleep until timeout
+ * @expires: timeout value (ktime_t)
+ * @delta: slack in expires timeout (ktime_t)
+ * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ * @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
+ */
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+ const enum hrtimer_mode mode, int clock)
+{
+ struct hrtimer_sleeper t;
+
+ /*
+ * Optimize when a zero timeout value is given. It does not
+ * matter whether this is an absolute or a relative time.
+ */
+ if (expires && !expires->tv64) {
+ __set_current_state(TASK_RUNNING);
+ return 0;
+ }
+
+ /*
+ * A NULL parameter means "infinite"
+ */
+ if (!expires) {
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ return -EINTR;
+ }
+
+ hrtimer_init_on_stack(&t.timer, clock, mode);
+ hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
+
+ hrtimer_init_sleeper(&t, current);
+
+ hrtimer_start_expires(&t.timer, mode);
+ if (!hrtimer_active(&t.timer))
+ t.task = NULL;
+
+ if (likely(t.task))
+ schedule();
+
+ hrtimer_cancel(&t.timer);
+ destroy_hrtimer_on_stack(&t.timer);
+
+ __set_current_state(TASK_RUNNING);
+
+ return !t.task ? 0 : -EINTR;
+}
+
+/**
+ * schedule_hrtimeout_range - sleep until timeout
+ * @expires: timeout value (ktime_t)
+ * @delta: slack in expires timeout (ktime_t)
+ * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+ const enum hrtimer_mode mode)
+{
+ return schedule_hrtimeout_range_clock(expires, delta, mode,
+ CLOCK_MONOTONIC);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires: timeout value (ktime_t)
+ * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+ const enum hrtimer_mode mode)
+{
+ return schedule_hrtimeout_range(expires, 0, mode);
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout);
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
new file mode 100644
index 000000000000..8d262b467573
--- /dev/null
+++ b/kernel/time/itimer.c
@@ -0,0 +1,301 @@
+/*
+ * linux/kernel/itimer.c
+ *
+ * Copyright (C) 1992 Darren Senn
+ */
+
+/* These are all the functions necessary to implement itimers */
+
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/syscalls.h>
+#include <linux/time.h>
+#include <linux/posix-timers.h>
+#include <linux/hrtimer.h>
+#include <trace/events/timer.h>
+
+#include <asm/uaccess.h>
+
+/**
+ * itimer_get_remtime - get remaining time for the timer
+ *
+ * @timer: the timer to read
+ *
+ * Returns the delta between the expiry time and now, which can be
+ * less than zero or 1usec for an pending expired timer
+ */
+static struct timeval itimer_get_remtime(struct hrtimer *timer)
+{
+ ktime_t rem = hrtimer_get_remaining(timer);
+
+ /*
+ * Racy but safe: if the itimer expires after the above
+ * hrtimer_get_remtime() call but before this condition
+ * then we return 0 - which is correct.
+ */
+ if (hrtimer_active(timer)) {
+ if (rem.tv64 <= 0)
+ rem.tv64 = NSEC_PER_USEC;
+ } else
+ rem.tv64 = 0;
+
+ return ktime_to_timeval(rem);
+}
+
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ struct itimerval *const value)
+{
+ cputime_t cval, cinterval;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ cval = it->expires;
+ cinterval = it->incr;
+ if (cval) {
+ struct task_cputime cputime;
+ cputime_t t;
+
+ thread_group_cputimer(tsk, &cputime);
+ if (clock_id == CPUCLOCK_PROF)
+ t = cputime.utime + cputime.stime;
+ else
+ /* CPUCLOCK_VIRT */
+ t = cputime.utime;
+
+ if (cval < t)
+ /* about to fire */
+ cval = cputime_one_jiffy;
+ else
+ cval = cval - t;
+ }
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ cputime_to_timeval(cval, &value->it_value);
+ cputime_to_timeval(cinterval, &value->it_interval);
+}
+
+int do_getitimer(int which, struct itimerval *value)
+{
+ struct task_struct *tsk = current;
+
+ switch (which) {
+ case ITIMER_REAL:
+ spin_lock_irq(&tsk->sighand->siglock);
+ value->it_value = itimer_get_remtime(&tsk->signal->real_timer);
+ value->it_interval =
+ ktime_to_timeval(tsk->signal->it_real_incr);
+ spin_unlock_irq(&tsk->sighand->siglock);
+ break;
+ case ITIMER_VIRTUAL:
+ get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
+ break;
+ case ITIMER_PROF:
+ get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
+ break;
+ default:
+ return(-EINVAL);
+ }
+ return 0;
+}
+
+SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value)
+{
+ int error = -EFAULT;
+ struct itimerval get_buffer;
+
+ if (value) {
+ error = do_getitimer(which, &get_buffer);
+ if (!error &&
+ copy_to_user(value, &get_buffer, sizeof(get_buffer)))
+ error = -EFAULT;
+ }
+ return error;
+}
+
+
+/*
+ * The timer is automagically restarted, when interval != 0
+ */
+enum hrtimer_restart it_real_fn(struct hrtimer *timer)
+{
+ struct signal_struct *sig =
+ container_of(timer, struct signal_struct, real_timer);
+
+ trace_itimer_expire(ITIMER_REAL, sig->leader_pid, 0);
+ kill_pid_info(SIGALRM, SEND_SIG_PRIV, sig->leader_pid);
+
+ return HRTIMER_NORESTART;
+}
+
+static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
+{
+ struct timespec ts;
+ s64 cpu_ns;
+
+ cputime_to_timespec(ct, &ts);
+ cpu_ns = timespec_to_ns(&ts);
+
+ return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+ const struct itimerval *const value,
+ struct itimerval *const ovalue)
+{
+ cputime_t cval, nval, cinterval, ninterval;
+ s64 ns_ninterval, ns_nval;
+ u32 error, incr_error;
+ struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+ nval = timeval_to_cputime(&value->it_value);
+ ns_nval = timeval_to_ns(&value->it_value);
+ ninterval = timeval_to_cputime(&value->it_interval);
+ ns_ninterval = timeval_to_ns(&value->it_interval);
+
+ error = cputime_sub_ns(nval, ns_nval);
+ incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+
+ spin_lock_irq(&tsk->sighand->siglock);
+
+ cval = it->expires;
+ cinterval = it->incr;
+ if (cval || nval) {
+ if (nval > 0)
+ nval += cputime_one_jiffy;
+ set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+ }
+ it->expires = nval;
+ it->incr = ninterval;
+ it->error = error;
+ it->incr_error = incr_error;
+ trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
+ ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
+
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ if (ovalue) {
+ cputime_to_timeval(cval, &ovalue->it_value);
+ cputime_to_timeval(cinterval, &ovalue->it_interval);
+ }
+}
+
+/*
+ * Returns true if the timeval is in canonical form
+ */
+#define timeval_valid(t) \
+ (((t)->tv_sec >= 0) && (((unsigned long) (t)->tv_usec) < USEC_PER_SEC))
+
+int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
+{
+ struct task_struct *tsk = current;
+ struct hrtimer *timer;
+ ktime_t expires;
+
+ /*
+ * Validate the timevals in value.
+ */
+ if (!timeval_valid(&value->it_value) ||
+ !timeval_valid(&value->it_interval))
+ return -EINVAL;
+
+ switch (which) {
+ case ITIMER_REAL:
+again:
+ spin_lock_irq(&tsk->sighand->siglock);
+ timer = &tsk->signal->real_timer;
+ if (ovalue) {
+ ovalue->it_value = itimer_get_remtime(timer);
+ ovalue->it_interval
+ = ktime_to_timeval(tsk->signal->it_real_incr);
+ }
+ /* We are sharing ->siglock with it_real_fn() */
+ if (hrtimer_try_to_cancel(timer) < 0) {
+ spin_unlock_irq(&tsk->sighand->siglock);
+ goto again;
+ }
+ expires = timeval_to_ktime(value->it_value);
+ if (expires.tv64 != 0) {
+ tsk->signal->it_real_incr =
+ timeval_to_ktime(value->it_interval);
+ hrtimer_start(timer, expires, HRTIMER_MODE_REL);
+ } else
+ tsk->signal->it_real_incr.tv64 = 0;
+
+ trace_itimer_state(ITIMER_REAL, value, 0);
+ spin_unlock_irq(&tsk->sighand->siglock);
+ break;
+ case ITIMER_VIRTUAL:
+ set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
+ break;
+ case ITIMER_PROF:
+ set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/**
+ * alarm_setitimer - set alarm in seconds
+ *
+ * @seconds: number of seconds until alarm
+ * 0 disables the alarm
+ *
+ * Returns the remaining time in seconds of a pending timer or 0 when
+ * the timer is not active.
+ *
+ * On 32 bit machines the seconds value is limited to (INT_MAX/2) to avoid
+ * negative timeval settings which would cause immediate expiry.
+ */
+unsigned int alarm_setitimer(unsigned int seconds)
+{
+ struct itimerval it_new, it_old;
+
+#if BITS_PER_LONG < 64
+ if (seconds > INT_MAX)
+ seconds = INT_MAX;
+#endif
+ it_new.it_value.tv_sec = seconds;
+ it_new.it_value.tv_usec = 0;
+ it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
+
+ do_setitimer(ITIMER_REAL, &it_new, &it_old);
+
+ /*
+ * We can't return 0 if we have an alarm pending ... And we'd
+ * better return too much than too little anyway
+ */
+ if ((!it_old.it_value.tv_sec && it_old.it_value.tv_usec) ||
+ it_old.it_value.tv_usec >= 500000)
+ it_old.it_value.tv_sec++;
+
+ return it_old.it_value.tv_sec;
+}
+
+SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
+ struct itimerval __user *, ovalue)
+{
+ struct itimerval set_buffer, get_buffer;
+ int error;
+
+ if (value) {
+ if(copy_from_user(&set_buffer, value, sizeof(set_buffer)))
+ return -EFAULT;
+ } else {
+ memset(&set_buffer, 0, sizeof(set_buffer));
+ printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+ " Misfeature support will be removed\n",
+ current->comm);
+ }
+
+ error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
+ if (error || !ovalue)
+ return error;
+
+ if (copy_to_user(ovalue, &get_buffer, sizeof(get_buffer)))
+ return -EFAULT;
+ return 0;
+}
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
new file mode 100644
index 000000000000..3b8946416a5f
--- /dev/null
+++ b/kernel/time/posix-cpu-timers.c
@@ -0,0 +1,1490 @@
+/*
+ * Implement CPU time clocks for the POSIX clock interface.
+ */
+
+#include <linux/sched.h>
+#include <linux/posix-timers.h>
+#include <linux/errno.h>
+#include <linux/math64.h>
+#include <asm/uaccess.h>
+#include <linux/kernel_stat.h>
+#include <trace/events/timer.h>
+#include <linux/random.h>
+#include <linux/tick.h>
+#include <linux/workqueue.h>
+
+/*
+ * Called after updating RLIMIT_CPU to run cpu timer and update
+ * tsk->signal->cputime_expires expiration cache if necessary. Needs
+ * siglock protection since other code may update expiration cache as
+ * well.
+ */
+void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
+{
+ cputime_t cputime = secs_to_cputime(rlim_new);
+
+ spin_lock_irq(&task->sighand->siglock);
+ set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+ spin_unlock_irq(&task->sighand->siglock);
+}
+
+static int check_clock(const clockid_t which_clock)
+{
+ int error = 0;
+ struct task_struct *p;
+ const pid_t pid = CPUCLOCK_PID(which_clock);
+
+ if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX)
+ return -EINVAL;
+
+ if (pid == 0)
+ return 0;
+
+ rcu_read_lock();
+ p = find_task_by_vpid(pid);
+ if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
+ same_thread_group(p, current) : has_group_leader_pid(p))) {
+ error = -EINVAL;
+ }
+ rcu_read_unlock();
+
+ return error;
+}
+
+static inline unsigned long long
+timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
+{
+ unsigned long long ret;
+
+ ret = 0; /* high half always zero when .cpu used */
+ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
+ ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
+ } else {
+ ret = cputime_to_expires(timespec_to_cputime(tp));
+ }
+ return ret;
+}
+
+static void sample_to_timespec(const clockid_t which_clock,
+ unsigned long long expires,
+ struct timespec *tp)
+{
+ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
+ *tp = ns_to_timespec(expires);
+ else
+ cputime_to_timespec((__force cputime_t)expires, tp);
+}
+
+/*
+ * Update expiry time from increment, and increase overrun count,
+ * given the current clock sample.
+ */
+static void bump_cpu_timer(struct k_itimer *timer,
+ unsigned long long now)
+{
+ int i;
+ unsigned long long delta, incr;
+
+ if (timer->it.cpu.incr == 0)
+ return;
+
+ if (now < timer->it.cpu.expires)
+ return;
+
+ incr = timer->it.cpu.incr;
+ delta = now + incr - timer->it.cpu.expires;
+
+ /* Don't use (incr*2 < delta), incr*2 might overflow. */
+ for (i = 0; incr < delta - incr; i++)
+ incr = incr << 1;
+
+ for (; i >= 0; incr >>= 1, i--) {
+ if (delta < incr)
+ continue;
+
+ timer->it.cpu.expires += incr;
+ timer->it_overrun += 1 << i;
+ delta -= incr;
+ }
+}
+
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime: The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero. Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
+{
+ if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime)
+ return 1;
+ return 0;
+}
+
+static inline unsigned long long prof_ticks(struct task_struct *p)
+{
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+
+ return cputime_to_expires(utime + stime);
+}
+static inline unsigned long long virt_ticks(struct task_struct *p)
+{
+ cputime_t utime;
+
+ task_cputime(p, &utime, NULL);
+
+ return cputime_to_expires(utime);
+}
+
+static int
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+{
+ int error = check_clock(which_clock);
+ if (!error) {
+ tp->tv_sec = 0;
+ tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ);
+ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
+ /*
+ * If sched_clock is using a cycle counter, we
+ * don't have any idea of its true resolution
+ * exported, but it is much more than 1s/HZ.
+ */
+ tp->tv_nsec = 1;
+ }
+ }
+ return error;
+}
+
+static int
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+{
+ /*
+ * You can never reset a CPU clock, but we check for other errors
+ * in the call before failing with EPERM.
+ */
+ int error = check_clock(which_clock);
+ if (error == 0) {
+ error = -EPERM;
+ }
+ return error;
+}
+
+
+/*
+ * Sample a per-thread clock for the given task.
+ */
+static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
+ unsigned long long *sample)
+{
+ switch (CPUCLOCK_WHICH(which_clock)) {
+ default:
+ return -EINVAL;
+ case CPUCLOCK_PROF:
+ *sample = prof_ticks(p);
+ break;
+ case CPUCLOCK_VIRT:
+ *sample = virt_ticks(p);
+ break;
+ case CPUCLOCK_SCHED:
+ *sample = task_sched_runtime(p);
+ break;
+ }
+ return 0;
+}
+
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+ if (b->utime > a->utime)
+ a->utime = b->utime;
+
+ if (b->stime > a->stime)
+ a->stime = b->stime;
+
+ if (b->sum_exec_runtime > a->sum_exec_runtime)
+ a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+ struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+ struct task_cputime sum;
+ unsigned long flags;
+
+ if (!cputimer->running) {
+ /*
+ * The POSIX timer interface allows for absolute time expiry
+ * values through the TIMER_ABSTIME flag, therefore we have
+ * to synchronize the timer to the clock every time we start
+ * it.
+ */
+ thread_group_cputime(tsk, &sum);
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
+ cputimer->running = 1;
+ update_gt_cputime(&cputimer->cputime, &sum);
+ } else
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
+ *times = cputimer->cputime;
+ raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
+/*
+ * Sample a process (thread group) clock for the given group_leader task.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
+ */
+static int cpu_clock_sample_group(const clockid_t which_clock,
+ struct task_struct *p,
+ unsigned long long *sample)
+{
+ struct task_cputime cputime;
+
+ switch (CPUCLOCK_WHICH(which_clock)) {
+ default:
+ return -EINVAL;
+ case CPUCLOCK_PROF:
+ thread_group_cputime(p, &cputime);
+ *sample = cputime_to_expires(cputime.utime + cputime.stime);
+ break;
+ case CPUCLOCK_VIRT:
+ thread_group_cputime(p, &cputime);
+ *sample = cputime_to_expires(cputime.utime);
+ break;
+ case CPUCLOCK_SCHED:
+ thread_group_cputime(p, &cputime);
+ *sample = cputime.sum_exec_runtime;
+ break;
+ }
+ return 0;
+}
+
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+ const clockid_t which_clock,
+ struct timespec *tp)
+{
+ int err = -EINVAL;
+ unsigned long long rtn;
+
+ if (CPUCLOCK_PERTHREAD(which_clock)) {
+ if (same_thread_group(tsk, current))
+ err = cpu_clock_sample(which_clock, tsk, &rtn);
+ } else {
+ unsigned long flags;
+ struct sighand_struct *sighand;
+
+ /*
+ * while_each_thread() is not yet entirely RCU safe,
+ * keep locking the group while sampling process
+ * clock for now.
+ */
+ sighand = lock_task_sighand(tsk, &flags);
+ if (!sighand)
+ return err;
+
+ if (tsk == current || thread_group_leader(tsk))
+ err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+ unlock_task_sighand(tsk, &flags);
+ }
+
+ if (!err)
+ sample_to_timespec(which_clock, rtn, tp);
+
+ return err;
+}
+
+
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+{
+ const pid_t pid = CPUCLOCK_PID(which_clock);
+ int err = -EINVAL;
+
+ if (pid == 0) {
+ /*
+ * Special case constant value for our own clocks.
+ * We don't have to do any lookup to find ourselves.
+ */
+ err = posix_cpu_clock_get_task(current, which_clock, tp);
+ } else {
+ /*
+ * Find the given PID, and validate that the caller
+ * should be able to see it.
+ */
+ struct task_struct *p;
+ rcu_read_lock();
+ p = find_task_by_vpid(pid);
+ if (p)
+ err = posix_cpu_clock_get_task(p, which_clock, tp);
+ rcu_read_unlock();
+ }
+
+ return err;
+}
+
+
+/*
+ * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
+ * This is called from sys_timer_create() and do_cpu_nanosleep() with the
+ * new timer already all-zeros initialized.
+ */
+static int posix_cpu_timer_create(struct k_itimer *new_timer)
+{
+ int ret = 0;
+ const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
+ struct task_struct *p;
+
+ if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX)
+ return -EINVAL;
+
+ INIT_LIST_HEAD(&new_timer->it.cpu.entry);
+
+ rcu_read_lock();
+ if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
+ if (pid == 0) {
+ p = current;
+ } else {
+ p = find_task_by_vpid(pid);
+ if (p && !same_thread_group(p, current))
+ p = NULL;
+ }
+ } else {
+ if (pid == 0) {
+ p = current->group_leader;
+ } else {
+ p = find_task_by_vpid(pid);
+ if (p && !has_group_leader_pid(p))
+ p = NULL;
+ }
+ }
+ new_timer->it.cpu.task = p;
+ if (p) {
+ get_task_struct(p);
+ } else {
+ ret = -EINVAL;
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+/*
+ * Clean up a CPU-clock timer that is about to be destroyed.
+ * This is called from timer deletion with the timer already locked.
+ * If we return TIMER_RETRY, it's necessary to release the timer's lock
+ * and try again. (This happens when the timer is in the middle of firing.)
+ */
+static int posix_cpu_timer_del(struct k_itimer *timer)
+{
+ int ret = 0;
+ unsigned long flags;
+ struct sighand_struct *sighand;
+ struct task_struct *p = timer->it.cpu.task;
+
+ WARN_ON_ONCE(p == NULL);
+
+ /*
+ * Protect against sighand release/switch in exit/exec and process/
+ * thread timer list entry concurrent read/writes.
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
+ /*
+ * We raced with the reaping of the task.
+ * The deletion should have cleared us off the list.
+ */
+ WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
+ } else {
+ if (timer->it.cpu.firing)
+ ret = TIMER_RETRY;
+ else
+ list_del(&timer->it.cpu.entry);
+
+ unlock_task_sighand(p, &flags);
+ }
+
+ if (!ret)
+ put_task_struct(p);
+
+ return ret;
+}
+
+static void cleanup_timers_list(struct list_head *head)
+{
+ struct cpu_timer_list *timer, *next;
+
+ list_for_each_entry_safe(timer, next, head, entry)
+ list_del_init(&timer->entry);
+}
+
+/*
+ * Clean out CPU timers still ticking when a thread exited. The task
+ * pointer is cleared, and the expiry time is replaced with the residual
+ * time for later timer_gettime calls to return.
+ * This must be called with the siglock held.
+ */
+static void cleanup_timers(struct list_head *head)
+{
+ cleanup_timers_list(head);
+ cleanup_timers_list(++head);
+ cleanup_timers_list(++head);
+}
+
+/*
+ * These are both called with the siglock held, when the current thread
+ * is being reaped. When the final (leader) thread in the group is reaped,
+ * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit.
+ */
+void posix_cpu_timers_exit(struct task_struct *tsk)
+{
+ add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
+ sizeof(unsigned long long));
+ cleanup_timers(tsk->cpu_timers);
+
+}
+void posix_cpu_timers_exit_group(struct task_struct *tsk)
+{
+ cleanup_timers(tsk->signal->cpu_timers);
+}
+
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+ return expires == 0 || expires > new_exp;
+}
+
+/*
+ * Insert the timer on the appropriate list before any timers that
+ * expire later. This must be called with the sighand lock held.
+ */
+static void arm_timer(struct k_itimer *timer)
+{
+ struct task_struct *p = timer->it.cpu.task;
+ struct list_head *head, *listpos;
+ struct task_cputime *cputime_expires;
+ struct cpu_timer_list *const nt = &timer->it.cpu;
+ struct cpu_timer_list *next;
+
+ if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ head = p->cpu_timers;
+ cputime_expires = &p->cputime_expires;
+ } else {
+ head = p->signal->cpu_timers;
+ cputime_expires = &p->signal->cputime_expires;
+ }
+ head += CPUCLOCK_WHICH(timer->it_clock);
+
+ listpos = head;
+ list_for_each_entry(next, head, entry) {
+ if (nt->expires < next->expires)
+ break;
+ listpos = &next->entry;
+ }
+ list_add(&nt->entry, listpos);
+
+ if (listpos == head) {
+ unsigned long long exp = nt->expires;
+
+ /*
+ * We are the new earliest-expiring POSIX 1.b timer, hence
+ * need to update expiration cache. Take into account that
+ * for process timers we share expiration cache with itimers
+ * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME.
+ */
+
+ switch (CPUCLOCK_WHICH(timer->it_clock)) {
+ case CPUCLOCK_PROF:
+ if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
+ cputime_expires->prof_exp = expires_to_cputime(exp);
+ break;
+ case CPUCLOCK_VIRT:
+ if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
+ cputime_expires->virt_exp = expires_to_cputime(exp);
+ break;
+ case CPUCLOCK_SCHED:
+ if (cputime_expires->sched_exp == 0 ||
+ cputime_expires->sched_exp > exp)
+ cputime_expires->sched_exp = exp;
+ break;
+ }
+ }
+}
+
+/*
+ * The timer is locked, fire it and arrange for its reload.
+ */
+static void cpu_timer_fire(struct k_itimer *timer)
+{
+ if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
+ /*
+ * User don't want any signal.
+ */
+ timer->it.cpu.expires = 0;
+ } else if (unlikely(timer->sigq == NULL)) {
+ /*
+ * This a special case for clock_nanosleep,
+ * not a normal timer from sys_timer_create.
+ */
+ wake_up_process(timer->it_process);
+ timer->it.cpu.expires = 0;
+ } else if (timer->it.cpu.incr == 0) {
+ /*
+ * One-shot timer. Clear it as soon as it's fired.
+ */
+ posix_timer_event(timer, 0);
+ timer->it.cpu.expires = 0;
+ } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
+ /*
+ * The signal did not get queued because the signal
+ * was ignored, so we won't get any callback to
+ * reload the timer. But we need to keep it
+ * ticking in case the signal is deliverable next time.
+ */
+ posix_cpu_timer_schedule(timer);
+ }
+}
+
+/*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+ struct task_struct *p,
+ unsigned long long *sample)
+{
+ struct task_cputime cputime;
+
+ thread_group_cputimer(p, &cputime);
+ switch (CPUCLOCK_WHICH(which_clock)) {
+ default:
+ return -EINVAL;
+ case CPUCLOCK_PROF:
+ *sample = cputime_to_expires(cputime.utime + cputime.stime);
+ break;
+ case CPUCLOCK_VIRT:
+ *sample = cputime_to_expires(cputime.utime);
+ break;
+ case CPUCLOCK_SCHED:
+ *sample = cputime.sum_exec_runtime + task_delta_exec(p);
+ break;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+static void nohz_kick_work_fn(struct work_struct *work)
+{
+ tick_nohz_full_kick_all();
+}
+
+static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
+
+/*
+ * We need the IPIs to be sent from sane process context.
+ * The posix cpu timers are always set with irqs disabled.
+ */
+static void posix_cpu_timer_kick_nohz(void)
+{
+ if (context_tracking_is_enabled())
+ schedule_work(&nohz_kick_work);
+}
+
+bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
+{
+ if (!task_cputime_zero(&tsk->cputime_expires))
+ return false;
+
+ if (tsk->signal->cputimer.running)
+ return false;
+
+ return true;
+}
+#else
+static inline void posix_cpu_timer_kick_nohz(void) { }
+#endif
+
+/*
+ * Guts of sys_timer_settime for CPU timers.
+ * This is called with the timer locked and interrupts disabled.
+ * If we return TIMER_RETRY, it's necessary to release the timer's lock
+ * and try again. (This happens when the timer is in the middle of firing.)
+ */
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
+ struct itimerspec *new, struct itimerspec *old)
+{
+ unsigned long flags;
+ struct sighand_struct *sighand;
+ struct task_struct *p = timer->it.cpu.task;
+ unsigned long long old_expires, new_expires, old_incr, val;
+ int ret;
+
+ WARN_ON_ONCE(p == NULL);
+
+ new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
+
+ /*
+ * Protect against sighand release/switch in exit/exec and p->cpu_timers
+ * and p->signal->cpu_timers read/write in arm_timer()
+ */
+ sighand = lock_task_sighand(p, &flags);
+ /*
+ * If p has just been reaped, we can no
+ * longer get any information about it at all.
+ */
+ if (unlikely(sighand == NULL)) {
+ return -ESRCH;
+ }
+
+ /*
+ * Disarm any old timer after extracting its expiry time.
+ */
+ WARN_ON_ONCE(!irqs_disabled());
+
+ ret = 0;
+ old_incr = timer->it.cpu.incr;
+ old_expires = timer->it.cpu.expires;
+ if (unlikely(timer->it.cpu.firing)) {
+ timer->it.cpu.firing = -1;
+ ret = TIMER_RETRY;
+ } else
+ list_del_init(&timer->it.cpu.entry);
+
+ /*
+ * We need to sample the current value to convert the new
+ * value from to relative and absolute, and to convert the
+ * old value from absolute to relative. To set a process
+ * timer, we need a sample to balance the thread expiry
+ * times (in arm_timer). With an absolute time, we must
+ * check if it's already passed. In short, we need a sample.
+ */
+ if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ cpu_clock_sample(timer->it_clock, p, &val);
+ } else {
+ cpu_timer_sample_group(timer->it_clock, p, &val);
+ }
+
+ if (old) {
+ if (old_expires == 0) {
+ old->it_value.tv_sec = 0;
+ old->it_value.tv_nsec = 0;
+ } else {
+ /*
+ * Update the timer in case it has
+ * overrun already. If it has,
+ * we'll report it as having overrun
+ * and with the next reloaded timer
+ * already ticking, though we are
+ * swallowing that pending
+ * notification here to install the
+ * new setting.
+ */
+ bump_cpu_timer(timer, val);
+ if (val < timer->it.cpu.expires) {
+ old_expires = timer->it.cpu.expires - val;
+ sample_to_timespec(timer->it_clock,
+ old_expires,
+ &old->it_value);
+ } else {
+ old->it_value.tv_nsec = 1;
+ old->it_value.tv_sec = 0;
+ }
+ }
+ }
+
+ if (unlikely(ret)) {
+ /*
+ * We are colliding with the timer actually firing.
+ * Punt after filling in the timer's old value, and
+ * disable this firing since we are already reporting
+ * it as an overrun (thanks to bump_cpu_timer above).
+ */
+ unlock_task_sighand(p, &flags);
+ goto out;
+ }
+
+ if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
+ new_expires += val;
+ }
+
+ /*
+ * Install the new expiry time (or zero).
+ * For a timer with no notification action, we don't actually
+ * arm the timer (we'll just fake it for timer_gettime).
+ */
+ timer->it.cpu.expires = new_expires;
+ if (new_expires != 0 && val < new_expires) {
+ arm_timer(timer);
+ }
+
+ unlock_task_sighand(p, &flags);
+ /*
+ * Install the new reload setting, and
+ * set up the signal and overrun bookkeeping.
+ */
+ timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
+ &new->it_interval);
+
+ /*
+ * This acts as a modification timestamp for the timer,
+ * so any automatic reload attempt will punt on seeing
+ * that we have reset the timer manually.
+ */
+ timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
+ ~REQUEUE_PENDING;
+ timer->it_overrun_last = 0;
+ timer->it_overrun = -1;
+
+ if (new_expires != 0 && !(val < new_expires)) {
+ /*
+ * The designated time already passed, so we notify
+ * immediately, even if the thread never runs to
+ * accumulate more time on this clock.
+ */
+ cpu_timer_fire(timer);
+ }
+
+ ret = 0;
+ out:
+ if (old) {
+ sample_to_timespec(timer->it_clock,
+ old_incr, &old->it_interval);
+ }
+ if (!ret)
+ posix_cpu_timer_kick_nohz();
+ return ret;
+}
+
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+{
+ unsigned long long now;
+ struct task_struct *p = timer->it.cpu.task;
+
+ WARN_ON_ONCE(p == NULL);
+
+ /*
+ * Easy part: convert the reload time.
+ */
+ sample_to_timespec(timer->it_clock,
+ timer->it.cpu.incr, &itp->it_interval);
+
+ if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */
+ itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
+ return;
+ }
+
+ /*
+ * Sample the clock to take the difference with the expiry time.
+ */
+ if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ cpu_clock_sample(timer->it_clock, p, &now);
+ } else {
+ struct sighand_struct *sighand;
+ unsigned long flags;
+
+ /*
+ * Protect against sighand release/switch in exit/exec and
+ * also make timer sampling safe if it ends up calling
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
+ /*
+ * The process has been reaped.
+ * We can't even collect a sample any more.
+ * Call the timer disarmed, nothing else to do.
+ */
+ timer->it.cpu.expires = 0;
+ sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+ &itp->it_value);
+ } else {
+ cpu_timer_sample_group(timer->it_clock, p, &now);
+ unlock_task_sighand(p, &flags);
+ }
+ }
+
+ if (now < timer->it.cpu.expires) {
+ sample_to_timespec(timer->it_clock,
+ timer->it.cpu.expires - now,
+ &itp->it_value);
+ } else {
+ /*
+ * The timer should have expired already, but the firing
+ * hasn't taken place yet. Say it's just about to expire.
+ */
+ itp->it_value.tv_nsec = 1;
+ itp->it_value.tv_sec = 0;
+ }
+}
+
+static unsigned long long
+check_timers_list(struct list_head *timers,
+ struct list_head *firing,
+ unsigned long long curr)
+{
+ int maxfire = 20;
+
+ while (!list_empty(timers)) {
+ struct cpu_timer_list *t;
+
+ t = list_first_entry(timers, struct cpu_timer_list, entry);
+
+ if (!--maxfire || curr < t->expires)
+ return t->expires;
+
+ t->firing = 1;
+ list_move_tail(&t->entry, firing);
+ }
+
+ return 0;
+}
+
+/*
+ * Check for any per-thread CPU timers that have fired and move them off
+ * the tsk->cpu_timers[N] list onto the firing list. Here we update the
+ * tsk->it_*_expires values to reflect the remaining thread CPU timers.
+ */
+static void check_thread_timers(struct task_struct *tsk,
+ struct list_head *firing)
+{
+ struct list_head *timers = tsk->cpu_timers;
+ struct signal_struct *const sig = tsk->signal;
+ struct task_cputime *tsk_expires = &tsk->cputime_expires;
+ unsigned long long expires;
+ unsigned long soft;
+
+ expires = check_timers_list(timers, firing, prof_ticks(tsk));
+ tsk_expires->prof_exp = expires_to_cputime(expires);
+
+ expires = check_timers_list(++timers, firing, virt_ticks(tsk));
+ tsk_expires->virt_exp = expires_to_cputime(expires);
+
+ tsk_expires->sched_exp = check_timers_list(++timers, firing,
+ tsk->se.sum_exec_runtime);
+
+ /*
+ * Check for the special case thread timers.
+ */
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+ if (soft != RLIM_INFINITY) {
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
+
+ if (hard != RLIM_INFINITY &&
+ tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
+ /*
+ * At the hard limit, we just die.
+ * No need to calculate anything else now.
+ */
+ __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
+ return;
+ }
+ if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
+ /*
+ * At the soft limit, send a SIGXCPU every second.
+ */
+ if (soft < hard) {
+ soft += USEC_PER_SEC;
+ sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
+ }
+ printk(KERN_INFO
+ "RT Watchdog Timeout: %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ }
+ }
+}
+
+static void stop_process_timers(struct signal_struct *sig)
+{
+ struct thread_group_cputimer *cputimer = &sig->cputimer;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&cputimer->lock, flags);
+ cputimer->running = 0;
+ raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+ unsigned long long *expires,
+ unsigned long long cur_time, int signo)
+{
+ if (!it->expires)
+ return;
+
+ if (cur_time >= it->expires) {
+ if (it->incr) {
+ it->expires += it->incr;
+ it->error += it->incr_error;
+ if (it->error >= onecputick) {
+ it->expires -= cputime_one_jiffy;
+ it->error -= onecputick;
+ }
+ } else {
+ it->expires = 0;
+ }
+
+ trace_itimer_expire(signo == SIGPROF ?
+ ITIMER_PROF : ITIMER_VIRTUAL,
+ tsk->signal->leader_pid, cur_time);
+ __group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+ }
+
+ if (it->expires && (!*expires || it->expires < *expires)) {
+ *expires = it->expires;
+ }
+}
+
+/*
+ * Check for any per-thread CPU timers that have fired and move them
+ * off the tsk->*_timers list onto the firing list. Per-thread timers
+ * have already been taken off.
+ */
+static void check_process_timers(struct task_struct *tsk,
+ struct list_head *firing)
+{
+ struct signal_struct *const sig = tsk->signal;
+ unsigned long long utime, ptime, virt_expires, prof_expires;
+ unsigned long long sum_sched_runtime, sched_expires;
+ struct list_head *timers = sig->cpu_timers;
+ struct task_cputime cputime;
+ unsigned long soft;
+
+ /*
+ * Collect the current process totals.
+ */
+ thread_group_cputimer(tsk, &cputime);
+ utime = cputime_to_expires(cputime.utime);
+ ptime = utime + cputime_to_expires(cputime.stime);
+ sum_sched_runtime = cputime.sum_exec_runtime;
+
+ prof_expires = check_timers_list(timers, firing, ptime);
+ virt_expires = check_timers_list(++timers, firing, utime);
+ sched_expires = check_timers_list(++timers, firing, sum_sched_runtime);
+
+ /*
+ * Check for the special case process timers.
+ */
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+ SIGPROF);
+ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+ SIGVTALRM);
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ if (soft != RLIM_INFINITY) {
+ unsigned long psecs = cputime_to_secs(ptime);
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
+ cputime_t x;
+ if (psecs >= hard) {
+ /*
+ * At the hard limit, we just die.
+ * No need to calculate anything else now.
+ */
+ __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
+ return;
+ }
+ if (psecs >= soft) {
+ /*
+ * At the soft limit, send a SIGXCPU every second.
+ */
+ __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+ if (soft < hard) {
+ soft++;
+ sig->rlim[RLIMIT_CPU].rlim_cur = soft;
+ }
+ }
+ x = secs_to_cputime(soft);
+ if (!prof_expires || x < prof_expires) {
+ prof_expires = x;
+ }
+ }
+
+ sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
+ sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
+ sig->cputime_expires.sched_exp = sched_expires;
+ if (task_cputime_zero(&sig->cputime_expires))
+ stop_process_timers(sig);
+}
+
+/*
+ * This is called from the signal code (via do_schedule_next_timer)
+ * when the last timer signal was delivered and we have to reload the timer.
+ */
+void posix_cpu_timer_schedule(struct k_itimer *timer)
+{
+ struct sighand_struct *sighand;
+ unsigned long flags;
+ struct task_struct *p = timer->it.cpu.task;
+ unsigned long long now;
+
+ WARN_ON_ONCE(p == NULL);
+
+ /*
+ * Fetch the current sample and update the timer's expiry time.
+ */
+ if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+ cpu_clock_sample(timer->it_clock, p, &now);
+ bump_cpu_timer(timer, now);
+ if (unlikely(p->exit_state))
+ goto out;
+
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (!sighand)
+ goto out;
+ } else {
+ /*
+ * Protect arm_timer() and timer sampling in case of call to
+ * thread_group_cputime().
+ */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL)) {
+ /*
+ * The process has been reaped.
+ * We can't even collect a sample any more.
+ */
+ timer->it.cpu.expires = 0;
+ goto out;
+ } else if (unlikely(p->exit_state) && thread_group_empty(p)) {
+ unlock_task_sighand(p, &flags);
+ /* Optimizations: if the process is dying, no need to rearm */
+ goto out;
+ }
+ cpu_timer_sample_group(timer->it_clock, p, &now);
+ bump_cpu_timer(timer, now);
+ /* Leave the sighand locked for the call below. */
+ }
+
+ /*
+ * Now re-arm for the new expiry time.
+ */
+ WARN_ON_ONCE(!irqs_disabled());
+ arm_timer(timer);
+ unlock_task_sighand(p, &flags);
+
+ /* Kick full dynticks CPUs in case they need to tick on the new timer */
+ posix_cpu_timer_kick_nohz();
+out:
+ timer->it_overrun_last = timer->it_overrun;
+ timer->it_overrun = -1;
+ ++timer->it_requeue_pending;
+}
+
+/**
+ * task_cputime_expired - Compare two task_cputime entities.
+ *
+ * @sample: The task_cputime structure to be checked for expiration.
+ * @expires: Expiration times, against which @sample will be checked.
+ *
+ * Checks @sample against @expires to see if any field of @sample has expired.
+ * Returns true if any field of the former is greater than the corresponding
+ * field of the latter if the latter field is set. Otherwise returns false.
+ */
+static inline int task_cputime_expired(const struct task_cputime *sample,
+ const struct task_cputime *expires)
+{
+ if (expires->utime && sample->utime >= expires->utime)
+ return 1;
+ if (expires->stime && sample->utime + sample->stime >= expires->stime)
+ return 1;
+ if (expires->sum_exec_runtime != 0 &&
+ sample->sum_exec_runtime >= expires->sum_exec_runtime)
+ return 1;
+ return 0;
+}
+
+/**
+ * fastpath_timer_check - POSIX CPU timers fast path.
+ *
+ * @tsk: The task (thread) being checked.
+ *
+ * Check the task and thread group timers. If both are zero (there are no
+ * timers set) return false. Otherwise snapshot the task and thread group
+ * timers and compare them with the corresponding expiration times. Return
+ * true if a timer has expired, else return false.
+ */
+static inline int fastpath_timer_check(struct task_struct *tsk)
+{
+ struct signal_struct *sig;
+ cputime_t utime, stime;
+
+ task_cputime(tsk, &utime, &stime);
+
+ if (!task_cputime_zero(&tsk->cputime_expires)) {
+ struct task_cputime task_sample = {
+ .utime = utime,
+ .stime = stime,
+ .sum_exec_runtime = tsk->se.sum_exec_runtime
+ };
+
+ if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+ return 1;
+ }
+
+ sig = tsk->signal;
+ if (sig->cputimer.running) {
+ struct task_cputime group_sample;
+
+ raw_spin_lock(&sig->cputimer.lock);
+ group_sample = sig->cputimer.cputime;
+ raw_spin_unlock(&sig->cputimer.lock);
+
+ if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * This is called from the timer interrupt handler. The irq handler has
+ * already updated our counts. We need to check if any timers fire now.
+ * Interrupts are disabled.
+ */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+ LIST_HEAD(firing);
+ struct k_itimer *timer, *next;
+ unsigned long flags;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ /*
+ * The fast path checks that there are no expired thread or thread
+ * group timers. If that's so, just return.
+ */
+ if (!fastpath_timer_check(tsk))
+ return;
+
+ if (!lock_task_sighand(tsk, &flags))
+ return;
+ /*
+ * Here we take off tsk->signal->cpu_timers[N] and
+ * tsk->cpu_timers[N] all the timers that are firing, and
+ * put them on the firing list.
+ */
+ check_thread_timers(tsk, &firing);
+ /*
+ * If there are any active process wide timers (POSIX 1.b, itimers,
+ * RLIMIT_CPU) cputimer must be running.
+ */
+ if (tsk->signal->cputimer.running)
+ check_process_timers(tsk, &firing);
+
+ /*
+ * We must release these locks before taking any timer's lock.
+ * There is a potential race with timer deletion here, as the
+ * siglock now protects our private firing list. We have set
+ * the firing flag in each timer, so that a deletion attempt
+ * that gets the timer lock before we do will give it up and
+ * spin until we've taken care of that timer below.
+ */
+ unlock_task_sighand(tsk, &flags);
+
+ /*
+ * Now that all the timers on our list have the firing flag,
+ * no one will touch their list entries but us. We'll take
+ * each timer's lock before clearing its firing flag, so no
+ * timer call will interfere.
+ */
+ list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
+ int cpu_firing;
+
+ spin_lock(&timer->it_lock);
+ list_del_init(&timer->it.cpu.entry);
+ cpu_firing = timer->it.cpu.firing;
+ timer->it.cpu.firing = 0;
+ /*
+ * The firing flag is -1 if we collided with a reset
+ * of the timer, which already reported this
+ * almost-firing as an overrun. So don't generate an event.
+ */
+ if (likely(cpu_firing >= 0))
+ cpu_timer_fire(timer);
+ spin_unlock(&timer->it_lock);
+ }
+}
+
+/*
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
+ * The tsk->sighand->siglock must be held by the caller.
+ */
+void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
+ cputime_t *newval, cputime_t *oldval)
+{
+ unsigned long long now;
+
+ WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
+ cpu_timer_sample_group(clock_idx, tsk, &now);
+
+ if (oldval) {
+ /*
+ * We are setting itimer. The *oldval is absolute and we update
+ * it to be relative, *newval argument is relative and we update
+ * it to be absolute.
+ */
+ if (*oldval) {
+ if (*oldval <= now) {
+ /* Just about to fire. */
+ *oldval = cputime_one_jiffy;
+ } else {
+ *oldval -= now;
+ }
+ }
+
+ if (!*newval)
+ goto out;
+ *newval += now;
+ }
+
+ /*
+ * Update expiration cache if we are the earliest timer, or eventually
+ * RLIMIT_CPU limit is earlier than prof_exp cpu timer expire.
+ */
+ switch (clock_idx) {
+ case CPUCLOCK_PROF:
+ if (expires_gt(tsk->signal->cputime_expires.prof_exp, *newval))
+ tsk->signal->cputime_expires.prof_exp = *newval;
+ break;
+ case CPUCLOCK_VIRT:
+ if (expires_gt(tsk->signal->cputime_expires.virt_exp, *newval))
+ tsk->signal->cputime_expires.virt_exp = *newval;
+ break;
+ }
+out:
+ posix_cpu_timer_kick_nohz();
+}
+
+static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct itimerspec *it)
+{
+ struct k_itimer timer;
+ int error;
+
+ /*
+ * Set up a temporary timer and then wait for it to go off.
+ */
+ memset(&timer, 0, sizeof timer);
+ spin_lock_init(&timer.it_lock);
+ timer.it_clock = which_clock;
+ timer.it_overrun = -1;
+ error = posix_cpu_timer_create(&timer);
+ timer.it_process = current;
+ if (!error) {
+ static struct itimerspec zero_it;
+
+ memset(it, 0, sizeof *it);
+ it->it_value = *rqtp;
+
+ spin_lock_irq(&timer.it_lock);
+ error = posix_cpu_timer_set(&timer, flags, it, NULL);
+ if (error) {
+ spin_unlock_irq(&timer.it_lock);
+ return error;
+ }
+
+ while (!signal_pending(current)) {
+ if (timer.it.cpu.expires == 0) {
+ /*
+ * Our timer fired and was reset, below
+ * deletion can not fail.
+ */
+ posix_cpu_timer_del(&timer);
+ spin_unlock_irq(&timer.it_lock);
+ return 0;
+ }
+
+ /*
+ * Block until cpu_timer_fire (or a signal) wakes us.
+ */
+ __set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_irq(&timer.it_lock);
+ schedule();
+ spin_lock_irq(&timer.it_lock);
+ }
+
+ /*
+ * We were interrupted by a signal.
+ */
+ sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
+ error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
+ if (!error) {
+ /*
+ * Timer is now unarmed, deletion can not fail.
+ */
+ posix_cpu_timer_del(&timer);
+ }
+ spin_unlock_irq(&timer.it_lock);
+
+ while (error == TIMER_RETRY) {
+ /*
+ * We need to handle case when timer was or is in the
+ * middle of firing. In other cases we already freed
+ * resources.
+ */
+ spin_lock_irq(&timer.it_lock);
+ error = posix_cpu_timer_del(&timer);
+ spin_unlock_irq(&timer.it_lock);
+ }
+
+ if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
+ /*
+ * It actually did fire already.
+ */
+ return 0;
+ }
+
+ error = -ERESTART_RESTARTBLOCK;
+ }
+
+ return error;
+}
+
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
+
+static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp, struct timespec __user *rmtp)
+{
+ struct restart_block *restart_block =
+ &current_thread_info()->restart_block;
+ struct itimerspec it;
+ int error;
+
+ /*
+ * Diagnose required errors first.
+ */
+ if (CPUCLOCK_PERTHREAD(which_clock) &&
+ (CPUCLOCK_PID(which_clock) == 0 ||
+ CPUCLOCK_PID(which_clock) == current->pid))
+ return -EINVAL;
+
+ error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);
+
+ if (error == -ERESTART_RESTARTBLOCK) {
+
+ if (flags & TIMER_ABSTIME)
+ return -ERESTARTNOHAND;
+ /*
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ return -EFAULT;
+
+ restart_block->fn = posix_cpu_nsleep_restart;
+ restart_block->nanosleep.clockid = which_clock;
+ restart_block->nanosleep.rmtp = rmtp;
+ restart_block->nanosleep.expires = timespec_to_ns(rqtp);
+ }
+ return error;
+}
+
+static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+ clockid_t which_clock = restart_block->nanosleep.clockid;
+ struct timespec t;
+ struct itimerspec it;
+ int error;
+
+ t = ns_to_timespec(restart_block->nanosleep.expires);
+
+ error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
+
+ if (error == -ERESTART_RESTARTBLOCK) {
+ struct timespec __user *rmtp = restart_block->nanosleep.rmtp;
+ /*
+ * Report back to the user the time still remaining.
+ */
+ if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ return -EFAULT;
+
+ restart_block->nanosleep.expires = timespec_to_ns(&t);
+ }
+ return error;
+
+}
+
+#define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
+#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
+
+static int process_cpu_clock_getres(const clockid_t which_clock,
+ struct timespec *tp)
+{
+ return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
+}
+static int process_cpu_clock_get(const clockid_t which_clock,
+ struct timespec *tp)
+{
+ return posix_cpu_clock_get(PROCESS_CLOCK, tp);
+}
+static int process_cpu_timer_create(struct k_itimer *timer)
+{
+ timer->it_clock = PROCESS_CLOCK;
+ return posix_cpu_timer_create(timer);
+}
+static int process_cpu_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *rqtp,
+ struct timespec __user *rmtp)
+{
+ return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
+}
+static long process_cpu_nsleep_restart(struct restart_block *restart_block)
+{
+ return -EINVAL;
+}
+static int thread_cpu_clock_getres(const clockid_t which_clock,
+ struct timespec *tp)
+{
+ return posix_cpu_clock_getres(THREAD_CLOCK, tp);
+}
+static int thread_cpu_clock_get(const clockid_t which_clock,
+ struct timespec *tp)
+{
+ return posix_cpu_clock_get(THREAD_CLOCK, tp);
+}
+static int thread_cpu_timer_create(struct k_itimer *timer)
+{
+ timer->it_clock = THREAD_CLOCK;
+ return posix_cpu_timer_create(timer);
+}
+
+struct k_clock clock_posix_cpu = {
+ .clock_getres = posix_cpu_clock_getres,
+ .clock_set = posix_cpu_clock_set,
+ .clock_get = posix_cpu_clock_get,
+ .timer_create = posix_cpu_timer_create,
+ .nsleep = posix_cpu_nsleep,
+ .nsleep_restart = posix_cpu_nsleep_restart,
+ .timer_set = posix_cpu_timer_set,
+ .timer_del = posix_cpu_timer_del,
+ .timer_get = posix_cpu_timer_get,
+};
+
+static __init int init_posix_cpu_timers(void)
+{
+ struct k_clock process = {
+ .clock_getres = process_cpu_clock_getres,
+ .clock_get = process_cpu_clock_get,
+ .timer_create = process_cpu_timer_create,
+ .nsleep = process_cpu_nsleep,
+ .nsleep_restart = process_cpu_nsleep_restart,
+ };
+ struct k_clock thread = {
+ .clock_getres = thread_cpu_clock_getres,
+ .clock_get = thread_cpu_clock_get,
+ .timer_create = thread_cpu_timer_create,
+ };
+ struct timespec ts;
+
+ posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
+ posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+
+ cputime_to_timespec(cputime_one_jiffy, &ts);
+ onecputick = ts.tv_nsec;
+ WARN_ON(ts.tv_sec != 0);
+
+ return 0;
+}
+__initcall(init_posix_cpu_timers);
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
new file mode 100644
index 000000000000..424c2d4265c9
--- /dev/null
+++ b/kernel/time/posix-timers.c
@@ -0,0 +1,1121 @@
+/*
+ * linux/kernel/posix-timers.c
+ *
+ *
+ * 2002-10-15 Posix Clocks & timers
+ * by George Anzinger george@mvista.com
+ *
+ * Copyright (C) 2002 2003 by MontaVista Software.
+ *
+ * 2004-06-01 Fix CLOCK_REALTIME clock/timer TIMER_ABSTIME bug.
+ * Copyright (C) 2004 Boris Hu
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * MontaVista Software | 1237 East Arques Avenue | Sunnyvale | CA 94085 | USA
+ */
+
+/* These are all the functions necessary to implement
+ * POSIX clocks & timers
+ */
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/mutex.h>
+
+#include <asm/uaccess.h>
+#include <linux/list.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/hash.h>
+#include <linux/posix-clock.h>
+#include <linux/posix-timers.h>
+#include <linux/syscalls.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <linux/export.h>
+#include <linux/hashtable.h>
+
+/*
+ * Management arrays for POSIX timers. Timers are now kept in static hash table
+ * with 512 entries.
+ * Timer ids are allocated by local routine, which selects proper hash head by
+ * key, constructed from current->signal address and per signal struct counter.
+ * This keeps timer ids unique per process, but now they can intersect between
+ * processes.
+ */
+
+/*
+ * Lets keep our timers in a slab cache :-)
+ */
+static struct kmem_cache *posix_timers_cache;
+
+static DEFINE_HASHTABLE(posix_timers_hashtable, 9);
+static DEFINE_SPINLOCK(hash_lock);
+
+/*
+ * we assume that the new SIGEV_THREAD_ID shares no bits with the other
+ * SIGEV values. Here we put out an error if this assumption fails.
+ */
+#if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \
+ ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
+#error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
+#endif
+
+/*
+ * parisc wants ENOTSUP instead of EOPNOTSUPP
+ */
+#ifndef ENOTSUP
+# define ENANOSLEEP_NOTSUP EOPNOTSUPP
+#else
+# define ENANOSLEEP_NOTSUP ENOTSUP
+#endif
+
+/*
+ * The timer ID is turned into a timer address by idr_find().
+ * Verifying a valid ID consists of:
+ *
+ * a) checking that idr_find() returns other than -1.
+ * b) checking that the timer id matches the one in the timer itself.
+ * c) that the timer owner is in the callers thread group.
+ */
+
+/*
+ * CLOCKs: The POSIX standard calls for a couple of clocks and allows us
+ * to implement others. This structure defines the various
+ * clocks.
+ *
+ * RESOLUTION: Clock resolution is used to round up timer and interval
+ * times, NOT to report clock times, which are reported with as
+ * much resolution as the system can muster. In some cases this
+ * resolution may depend on the underlying clock hardware and
+ * may not be quantifiable until run time, and only then is the
+ * necessary code is written. The standard says we should say
+ * something about this issue in the documentation...
+ *
+ * FUNCTIONS: The CLOCKs structure defines possible functions to
+ * handle various clock functions.
+ *
+ * The standard POSIX timer management code assumes the
+ * following: 1.) The k_itimer struct (sched.h) is used for
+ * the timer. 2.) The list, it_lock, it_clock, it_id and
+ * it_pid fields are not modified by timer code.
+ *
+ * Permissions: It is assumed that the clock_settime() function defined
+ * for each clock will take care of permission checks. Some
+ * clocks may be set able by any user (i.e. local process
+ * clocks) others not. Currently the only set able clock we
+ * have is CLOCK_REALTIME and its high res counter part, both of
+ * which we beg off on and pass to do_sys_settimeofday().
+ */
+
+static struct k_clock posix_clocks[MAX_CLOCKS];
+
+/*
+ * These ones are defined below.
+ */
+static int common_nsleep(const clockid_t, int flags, struct timespec *t,
+ struct timespec __user *rmtp);
+static int common_timer_create(struct k_itimer *new_timer);
+static void common_timer_get(struct k_itimer *, struct itimerspec *);
+static int common_timer_set(struct k_itimer *, int,
+ struct itimerspec *, struct itimerspec *);
+static int common_timer_del(struct k_itimer *timer);
+
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
+
+static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags);
+
+#define lock_timer(tid, flags) \
+({ struct k_itimer *__timr; \
+ __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags)); \
+ __timr; \
+})
+
+static int hash(struct signal_struct *sig, unsigned int nr)
+{
+ return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable));
+}
+
+static struct k_itimer *__posix_timers_find(struct hlist_head *head,
+ struct signal_struct *sig,
+ timer_t id)
+{
+ struct k_itimer *timer;
+
+ hlist_for_each_entry_rcu(timer, head, t_hash) {
+ if ((timer->it_signal == sig) && (timer->it_id == id))
+ return timer;
+ }
+ return NULL;
+}
+
+static struct k_itimer *posix_timer_by_id(timer_t id)
+{
+ struct signal_struct *sig = current->signal;
+ struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)];
+
+ return __posix_timers_find(head, sig, id);
+}
+
+static int posix_timer_add(struct k_itimer *timer)
+{
+ struct signal_struct *sig = current->signal;
+ int first_free_id = sig->posix_timer_id;
+ struct hlist_head *head;
+ int ret = -ENOENT;
+
+ do {
+ spin_lock(&hash_lock);
+ head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)];
+ if (!__posix_timers_find(head, sig, sig->posix_timer_id)) {
+ hlist_add_head_rcu(&timer->t_hash, head);
+ ret = sig->posix_timer_id;
+ }
+ if (++sig->posix_timer_id < 0)
+ sig->posix_timer_id = 0;
+ if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT))
+ /* Loop over all possible ids completed */
+ ret = -EAGAIN;
+ spin_unlock(&hash_lock);
+ } while (ret == -ENOENT);
+ return ret;
+}
+
+static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
+{
+ spin_unlock_irqrestore(&timr->it_lock, flags);
+}
+
+/* Get clock_realtime */
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
+{
+ ktime_get_real_ts(tp);
+ return 0;
+}
+
+/* Set clock_realtime */
+static int posix_clock_realtime_set(const clockid_t which_clock,
+ const struct timespec *tp)
+{
+ return do_sys_settimeofday(tp, NULL);
+}
+
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+ struct timex *t)
+{
+ return do_adjtimex(t);
+}
+
+/*
+ * Get monotonic time for posix timers
+ */
+static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
+{
+ ktime_get_ts(tp);
+ return 0;
+}
+
+/*
+ * Get monotonic-raw time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+ getrawmonotonic(tp);
+ return 0;
+}
+
+
+static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
+{
+ *tp = current_kernel_time();
+ return 0;
+}
+
+static int posix_get_monotonic_coarse(clockid_t which_clock,
+ struct timespec *tp)
+{
+ *tp = get_monotonic_coarse();
+ return 0;
+}
+
+static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+{
+ *tp = ktime_to_timespec(KTIME_LOW_RES);
+ return 0;
+}
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+ get_monotonic_boottime(tp);
+ return 0;
+}
+
+static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+{
+ timekeeping_clocktai(tp);
+ return 0;
+}
+
+/*
+ * Initialize everything, well, just everything in Posix clocks/timers ;)
+ */
+static __init int init_posix_timers(void)
+{
+ struct k_clock clock_realtime = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_clock_realtime_get,
+ .clock_set = posix_clock_realtime_set,
+ .clock_adj = posix_clock_realtime_adj,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
+ struct k_clock clock_monotonic = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_ktime_get_ts,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
+ struct k_clock clock_monotonic_raw = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_monotonic_raw,
+ };
+ struct k_clock clock_realtime_coarse = {
+ .clock_getres = posix_get_coarse_res,
+ .clock_get = posix_get_realtime_coarse,
+ };
+ struct k_clock clock_monotonic_coarse = {
+ .clock_getres = posix_get_coarse_res,
+ .clock_get = posix_get_monotonic_coarse,
+ };
+ struct k_clock clock_tai = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_tai,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
+ struct k_clock clock_boottime = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_boottime,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
+
+ posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+ posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+ posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+ posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+ posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+ posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
+ posix_timers_register_clock(CLOCK_TAI, &clock_tai);
+
+ posix_timers_cache = kmem_cache_create("posix_timers_cache",
+ sizeof (struct k_itimer), 0, SLAB_PANIC,
+ NULL);
+ return 0;
+}
+
+__initcall(init_posix_timers);
+
+static void schedule_next_timer(struct k_itimer *timr)
+{
+ struct hrtimer *timer = &timr->it.real.timer;
+
+ if (timr->it.real.interval.tv64 == 0)
+ return;
+
+ timr->it_overrun += (unsigned int) hrtimer_forward(timer,
+ timer->base->get_time(),
+ timr->it.real.interval);
+
+ timr->it_overrun_last = timr->it_overrun;
+ timr->it_overrun = -1;
+ ++timr->it_requeue_pending;
+ hrtimer_restart(timer);
+}
+
+/*
+ * This function is exported for use by the signal deliver code. It is
+ * called just prior to the info block being released and passes that
+ * block to us. It's function is to update the overrun entry AND to
+ * restart the timer. It should only be called if the timer is to be
+ * restarted (i.e. we have flagged this in the sys_private entry of the
+ * info block).
+ *
+ * To protect against the timer going away while the interrupt is queued,
+ * we require that the it_requeue_pending flag be set.
+ */
+void do_schedule_next_timer(struct siginfo *info)
+{
+ struct k_itimer *timr;
+ unsigned long flags;
+
+ timr = lock_timer(info->si_tid, &flags);
+
+ if (timr && timr->it_requeue_pending == info->si_sys_private) {
+ if (timr->it_clock < 0)
+ posix_cpu_timer_schedule(timr);
+ else
+ schedule_next_timer(timr);
+
+ info->si_overrun += timr->it_overrun_last;
+ }
+
+ if (timr)
+ unlock_timer(timr, flags);
+}
+
+int posix_timer_event(struct k_itimer *timr, int si_private)
+{
+ struct task_struct *task;
+ int shared, ret = -1;
+ /*
+ * FIXME: if ->sigq is queued we can race with
+ * dequeue_signal()->do_schedule_next_timer().
+ *
+ * If dequeue_signal() sees the "right" value of
+ * si_sys_private it calls do_schedule_next_timer().
+ * We re-queue ->sigq and drop ->it_lock().
+ * do_schedule_next_timer() locks the timer
+ * and re-schedules it while ->sigq is pending.
+ * Not really bad, but not that we want.
+ */
+ timr->sigq->info.si_sys_private = si_private;
+
+ rcu_read_lock();
+ task = pid_task(timr->it_pid, PIDTYPE_PID);
+ if (task) {
+ shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+ ret = send_sigqueue(timr->sigq, task, shared);
+ }
+ rcu_read_unlock();
+ /* If we failed to send the signal the timer stops. */
+ return ret > 0;
+}
+EXPORT_SYMBOL_GPL(posix_timer_event);
+
+/*
+ * This function gets called when a POSIX.1b interval timer expires. It
+ * is used as a callback from the kernel internal timer. The
+ * run_timer_list code ALWAYS calls with interrupts on.
+
+ * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers.
+ */
+static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
+{
+ struct k_itimer *timr;
+ unsigned long flags;
+ int si_private = 0;
+ enum hrtimer_restart ret = HRTIMER_NORESTART;
+
+ timr = container_of(timer, struct k_itimer, it.real.timer);
+ spin_lock_irqsave(&timr->it_lock, flags);
+
+ if (timr->it.real.interval.tv64 != 0)
+ si_private = ++timr->it_requeue_pending;
+
+ if (posix_timer_event(timr, si_private)) {
+ /*
+ * signal was not sent because of sig_ignor
+ * we will not get a call back to restart it AND
+ * it should be restarted.
+ */
+ if (timr->it.real.interval.tv64 != 0) {
+ ktime_t now = hrtimer_cb_get_time(timer);
+
+ /*
+ * FIXME: What we really want, is to stop this
+ * timer completely and restart it in case the
+ * SIG_IGN is removed. This is a non trivial
+ * change which involves sighand locking
+ * (sigh !), which we don't want to do late in
+ * the release cycle.
+ *
+ * For now we just let timers with an interval
+ * less than a jiffie expire every jiffie to
+ * avoid softirq starvation in case of SIG_IGN
+ * and a very small interval, which would put
+ * the timer right back on the softirq pending
+ * list. By moving now ahead of time we trick
+ * hrtimer_forward() to expire the timer
+ * later, while we still maintain the overrun
+ * accuracy, but have some inconsistency in
+ * the timer_gettime() case. This is at least
+ * better than a starved softirq. A more
+ * complex fix which solves also another related
+ * inconsistency is already in the pipeline.
+ */
+#ifdef CONFIG_HIGH_RES_TIMERS
+ {
+ ktime_t kj = ktime_set(0, NSEC_PER_SEC / HZ);
+
+ if (timr->it.real.interval.tv64 < kj.tv64)
+ now = ktime_add(now, kj);
+ }
+#endif
+ timr->it_overrun += (unsigned int)
+ hrtimer_forward(timer, now,
+ timr->it.real.interval);
+ ret = HRTIMER_RESTART;
+ ++timr->it_requeue_pending;
+ }
+ }
+
+ unlock_timer(timr, flags);
+ return ret;
+}
+
+static struct pid *good_sigevent(sigevent_t * event)
+{
+ struct task_struct *rtn = current->group_leader;
+
+ if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
+ (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
+ !same_thread_group(rtn, current) ||
+ (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
+ return NULL;
+
+ if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
+ ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
+ return NULL;
+
+ return task_pid(rtn);
+}
+
+void posix_timers_register_clock(const clockid_t clock_id,
+ struct k_clock *new_clock)
+{
+ if ((unsigned) clock_id >= MAX_CLOCKS) {
+ printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
+ clock_id);
+ return;
+ }
+
+ if (!new_clock->clock_get) {
+ printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
+ clock_id);
+ return;
+ }
+ if (!new_clock->clock_getres) {
+ printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
+ clock_id);
+ return;
+ }
+
+ posix_clocks[clock_id] = *new_clock;
+}
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
+
+static struct k_itimer * alloc_posix_timer(void)
+{
+ struct k_itimer *tmr;
+ tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
+ if (!tmr)
+ return tmr;
+ if (unlikely(!(tmr->sigq = sigqueue_alloc()))) {
+ kmem_cache_free(posix_timers_cache, tmr);
+ return NULL;
+ }
+ memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
+ return tmr;
+}
+
+static void k_itimer_rcu_free(struct rcu_head *head)
+{
+ struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+
+ kmem_cache_free(posix_timers_cache, tmr);
+}
+
+#define IT_ID_SET 1
+#define IT_ID_NOT_SET 0
+static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
+{
+ if (it_id_set) {
+ unsigned long flags;
+ spin_lock_irqsave(&hash_lock, flags);
+ hlist_del_rcu(&tmr->t_hash);
+ spin_unlock_irqrestore(&hash_lock, flags);
+ }
+ put_pid(tmr->it_pid);
+ sigqueue_free(tmr->sigq);
+ call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
+}
+
+static struct k_clock *clockid_to_kclock(const clockid_t id)
+{
+ if (id < 0)
+ return (id & CLOCKFD_MASK) == CLOCKFD ?
+ &clock_posix_dynamic : &clock_posix_cpu;
+
+ if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
+ return NULL;
+ return &posix_clocks[id];
+}
+
+static int common_timer_create(struct k_itimer *new_timer)
+{
+ hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0);
+ return 0;
+}
+
+/* Create a POSIX.1b interval timer. */
+
+SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
+ struct sigevent __user *, timer_event_spec,
+ timer_t __user *, created_timer_id)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct k_itimer *new_timer;
+ int error, new_timer_id;
+ sigevent_t event;
+ int it_id_set = IT_ID_NOT_SET;
+
+ if (!kc)
+ return -EINVAL;
+ if (!kc->timer_create)
+ return -EOPNOTSUPP;
+
+ new_timer = alloc_posix_timer();
+ if (unlikely(!new_timer))
+ return -EAGAIN;
+
+ spin_lock_init(&new_timer->it_lock);
+ new_timer_id = posix_timer_add(new_timer);
+ if (new_timer_id < 0) {
+ error = new_timer_id;
+ goto out;
+ }
+
+ it_id_set = IT_ID_SET;
+ new_timer->it_id = (timer_t) new_timer_id;
+ new_timer->it_clock = which_clock;
+ new_timer->it_overrun = -1;
+
+ if (timer_event_spec) {
+ if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
+ error = -EFAULT;
+ goto out;
+ }
+ rcu_read_lock();
+ new_timer->it_pid = get_pid(good_sigevent(&event));
+ rcu_read_unlock();
+ if (!new_timer->it_pid) {
+ error = -EINVAL;
+ goto out;
+ }
+ } else {
+ event.sigev_notify = SIGEV_SIGNAL;
+ event.sigev_signo = SIGALRM;
+ event.sigev_value.sival_int = new_timer->it_id;
+ new_timer->it_pid = get_pid(task_tgid(current));
+ }
+
+ 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;
+
+ if (copy_to_user(created_timer_id,
+ &new_timer_id, sizeof (new_timer_id))) {
+ error = -EFAULT;
+ goto out;
+ }
+
+ error = kc->timer_create(new_timer);
+ if (error)
+ goto out;
+
+ spin_lock_irq(&current->sighand->siglock);
+ new_timer->it_signal = current->signal;
+ 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:
+ release_posix_timer(new_timer, it_id_set);
+ return error;
+}
+
+/*
+ * Locking issues: We need to protect the result of the id look up until
+ * we get the timer locked down so it is not deleted under us. The
+ * removal is done under the idr spinlock so we use that here to bridge
+ * 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)
+{
+ struct k_itimer *timr;
+
+ /*
+ * timer_t could be any type >= int and we want to make sure any
+ * @timer_id outside positive int range fails lookup.
+ */
+ if ((unsigned long long)timer_id > INT_MAX)
+ return NULL;
+
+ rcu_read_lock();
+ timr = posix_timer_by_id(timer_id);
+ if (timr) {
+ spin_lock_irqsave(&timr->it_lock, *flags);
+ if (timr->it_signal == current->signal) {
+ rcu_read_unlock();
+ return timr;
+ }
+ spin_unlock_irqrestore(&timr->it_lock, *flags);
+ }
+ rcu_read_unlock();
+
+ return NULL;
+}
+
+/*
+ * Get the time remaining on a POSIX.1b interval timer. This function
+ * is ALWAYS called with spin_lock_irq on the timer, thus it must not
+ * mess with irq.
+ *
+ * We have a couple of messes to clean up here. First there is the case
+ * of a timer that has a requeue pending. These timers should appear to
+ * be in the timer list with an expiry as if we were to requeue them
+ * now.
+ *
+ * The second issue is the SIGEV_NONE timer which may be active but is
+ * not really ever put in the timer list (to save system resources).
+ * This timer may be expired, and if so, we will do it here. Otherwise
+ * it is the same as a requeue pending timer WRT to what we should
+ * report.
+ */
+static void
+common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
+{
+ ktime_t now, remaining, iv;
+ struct hrtimer *timer = &timr->it.real.timer;
+
+ memset(cur_setting, 0, sizeof(struct itimerspec));
+
+ iv = timr->it.real.interval;
+
+ /* interval timer ? */
+ if (iv.tv64)
+ cur_setting->it_interval = ktime_to_timespec(iv);
+ else if (!hrtimer_active(timer) &&
+ (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ return;
+
+ now = timer->base->get_time();
+
+ /*
+ * When a requeue is pending or this is a SIGEV_NONE
+ * timer move the expiry time forward by intervals, so
+ * expiry is > now.
+ */
+ if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
+ (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
+ timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+
+ remaining = ktime_sub(hrtimer_get_expires(timer), now);
+ /* Return 0 only, when the timer is expired and not pending */
+ if (remaining.tv64 <= 0) {
+ /*
+ * A single shot SIGEV_NONE timer must return 0, when
+ * it is expired !
+ */
+ if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ cur_setting->it_value.tv_nsec = 1;
+ } else
+ cur_setting->it_value = ktime_to_timespec(remaining);
+}
+
+/* Get the time remaining on a POSIX.1b interval timer. */
+SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
+ struct itimerspec __user *, setting)
+{
+ struct itimerspec cur_setting;
+ struct k_itimer *timr;
+ struct k_clock *kc;
+ unsigned long flags;
+ int ret = 0;
+
+ timr = lock_timer(timer_id, &flags);
+ if (!timr)
+ return -EINVAL;
+
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_get))
+ ret = -EINVAL;
+ else
+ kc->timer_get(timr, &cur_setting);
+
+ unlock_timer(timr, flags);
+
+ if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+ return -EFAULT;
+
+ return ret;
+}
+
+/*
+ * Get the number of overruns of a POSIX.1b interval timer. This is to
+ * be the overrun of the timer last delivered. At the same time we are
+ * accumulating overruns on the next timer. The overrun is frozen when
+ * the signal is delivered, either at the notify time (if the info block
+ * is not queued) or at the actual delivery time (as we are informed by
+ * the call back to do_schedule_next_timer(). So all we need to do is
+ * to pick up the frozen overrun.
+ */
+SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
+{
+ struct k_itimer *timr;
+ int overrun;
+ unsigned long flags;
+
+ timr = lock_timer(timer_id, &flags);
+ if (!timr)
+ return -EINVAL;
+
+ overrun = timr->it_overrun_last;
+ unlock_timer(timr, flags);
+
+ return overrun;
+}
+
+/* Set a POSIX.1b interval timer. */
+/* timr->it_lock is taken. */
+static int
+common_timer_set(struct k_itimer *timr, int flags,
+ struct itimerspec *new_setting, struct itimerspec *old_setting)
+{
+ struct hrtimer *timer = &timr->it.real.timer;
+ enum hrtimer_mode mode;
+
+ if (old_setting)
+ common_timer_get(timr, old_setting);
+
+ /* disable the timer */
+ timr->it.real.interval.tv64 = 0;
+ /*
+ * careful here. If smp we could be in the "fire" routine which will
+ * be spinning as we hold the lock. But this is ONLY an SMP issue.
+ */
+ if (hrtimer_try_to_cancel(timer) < 0)
+ return TIMER_RETRY;
+
+ timr->it_requeue_pending = (timr->it_requeue_pending + 2) &
+ ~REQUEUE_PENDING;
+ timr->it_overrun_last = 0;
+
+ /* switch off the timer when it_value is zero */
+ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec)
+ return 0;
+
+ mode = flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL;
+ hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
+ timr->it.real.timer.function = posix_timer_fn;
+
+ hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));
+
+ /* Convert interval */
+ timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
+
+ /* SIGEV_NONE timers are not queued ! See common_timer_get */
+ if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
+ /* Setup correct expiry time for relative timers */
+ if (mode == HRTIMER_MODE_REL) {
+ hrtimer_add_expires(timer, timer->base->get_time());
+ }
+ return 0;
+ }
+
+ hrtimer_start_expires(timer, mode);
+ return 0;
+}
+
+/* Set a POSIX.1b interval timer */
+SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
+ const struct itimerspec __user *, new_setting,
+ struct itimerspec __user *, old_setting)
+{
+ struct k_itimer *timr;
+ struct itimerspec new_spec, old_spec;
+ int error = 0;
+ unsigned long flag;
+ struct itimerspec *rtn = old_setting ? &old_spec : NULL;
+ struct k_clock *kc;
+
+ if (!new_setting)
+ return -EINVAL;
+
+ if (copy_from_user(&new_spec, new_setting, sizeof (new_spec)))
+ return -EFAULT;
+
+ if (!timespec_valid(&new_spec.it_interval) ||
+ !timespec_valid(&new_spec.it_value))
+ return -EINVAL;
+retry:
+ timr = lock_timer(timer_id, &flag);
+ if (!timr)
+ return -EINVAL;
+
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_set))
+ error = -EINVAL;
+ else
+ error = kc->timer_set(timr, flags, &new_spec, rtn);
+
+ unlock_timer(timr, flag);
+ if (error == TIMER_RETRY) {
+ rtn = NULL; // We already got the old time...
+ goto retry;
+ }
+
+ if (old_setting && !error &&
+ copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
+ error = -EFAULT;
+
+ return error;
+}
+
+static int common_timer_del(struct k_itimer *timer)
+{
+ timer->it.real.interval.tv64 = 0;
+
+ if (hrtimer_try_to_cancel(&timer->it.real.timer) < 0)
+ return TIMER_RETRY;
+ return 0;
+}
+
+static inline int timer_delete_hook(struct k_itimer *timer)
+{
+ struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+
+ if (WARN_ON_ONCE(!kc || !kc->timer_del))
+ return -EINVAL;
+ return kc->timer_del(timer);
+}
+
+/* Delete a POSIX.1b interval timer. */
+SYSCALL_DEFINE1(timer_delete, timer_t, timer_id)
+{
+ struct k_itimer *timer;
+ unsigned long flags;
+
+retry_delete:
+ timer = lock_timer(timer_id, &flags);
+ if (!timer)
+ return -EINVAL;
+
+ if (timer_delete_hook(timer) == TIMER_RETRY) {
+ unlock_timer(timer, flags);
+ goto retry_delete;
+ }
+
+ spin_lock(&current->sighand->siglock);
+ list_del(&timer->list);
+ spin_unlock(&current->sighand->siglock);
+ /*
+ * This keeps any tasks waiting on the spin lock from thinking
+ * they got something (see the lock code above).
+ */
+ timer->it_signal = NULL;
+
+ unlock_timer(timer, flags);
+ release_posix_timer(timer, IT_ID_SET);
+ return 0;
+}
+
+/*
+ * return timer owned by the process, used by exit_itimers
+ */
+static void itimer_delete(struct k_itimer *timer)
+{
+ unsigned long flags;
+
+retry_delete:
+ spin_lock_irqsave(&timer->it_lock, flags);
+
+ if (timer_delete_hook(timer) == TIMER_RETRY) {
+ unlock_timer(timer, flags);
+ goto retry_delete;
+ }
+ list_del(&timer->list);
+ /*
+ * This keeps any tasks waiting on the spin lock from thinking
+ * they got something (see the lock code above).
+ */
+ timer->it_signal = NULL;
+
+ unlock_timer(timer, flags);
+ release_posix_timer(timer, IT_ID_SET);
+}
+
+/*
+ * This is called by do_exit or de_thread, only when there are no more
+ * references to the shared signal_struct.
+ */
+void exit_itimers(struct signal_struct *sig)
+{
+ struct k_itimer *tmr;
+
+ while (!list_empty(&sig->posix_timers)) {
+ tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ itimer_delete(tmr);
+ }
+}
+
+SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
+ const struct timespec __user *, tp)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec new_tp;
+
+ if (!kc || !kc->clock_set)
+ return -EINVAL;
+
+ if (copy_from_user(&new_tp, tp, sizeof (*tp)))
+ return -EFAULT;
+
+ return kc->clock_set(which_clock, &new_tp);
+}
+
+SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
+ struct timespec __user *,tp)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec kernel_tp;
+ int error;
+
+ if (!kc)
+ return -EINVAL;
+
+ error = kc->clock_get(which_clock, &kernel_tp);
+
+ if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
+ error = -EFAULT;
+
+ return error;
+}
+
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+ struct timex __user *, utx)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timex ktx;
+ int err;
+
+ if (!kc)
+ return -EINVAL;
+ if (!kc->clock_adj)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&ktx, utx, sizeof(ktx)))
+ return -EFAULT;
+
+ err = kc->clock_adj(which_clock, &ktx);
+
+ if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
+ return -EFAULT;
+
+ return err;
+}
+
+SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
+ struct timespec __user *, tp)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec rtn_tp;
+ int error;
+
+ if (!kc)
+ return -EINVAL;
+
+ error = kc->clock_getres(which_clock, &rtn_tp);
+
+ if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
+ error = -EFAULT;
+
+ return error;
+}
+
+/*
+ * nanosleep for monotonic and realtime clocks
+ */
+static int common_nsleep(const clockid_t which_clock, int flags,
+ struct timespec *tsave, struct timespec __user *rmtp)
+{
+ return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
+ HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+ which_clock);
+}
+
+SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
+ const struct timespec __user *, rqtp,
+ struct timespec __user *, rmtp)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec t;
+
+ if (!kc)
+ return -EINVAL;
+ if (!kc->nsleep)
+ return -ENANOSLEEP_NOTSUP;
+
+ if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
+ return -EFAULT;
+
+ if (!timespec_valid(&t))
+ return -EINVAL;
+
+ return kc->nsleep(which_clock, flags, &t, rmtp);
+}
+
+/*
+ * This will restart clock_nanosleep. This is required only by
+ * compat_clock_nanosleep_restart for now.
+ */
+long clock_nanosleep_restart(struct restart_block *restart_block)
+{
+ clockid_t which_clock = restart_block->nanosleep.clockid;
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+
+ if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
+ return -EINVAL;
+
+ return kc->nsleep_restart(restart_block);
+}
diff --git a/kernel/time/time.c b/kernel/time/time.c
new file mode 100644
index 000000000000..7c7964c33ae7
--- /dev/null
+++ b/kernel/time/time.c
@@ -0,0 +1,714 @@
+/*
+ * linux/kernel/time.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * This file contains the interface functions for the various
+ * time related system calls: time, stime, gettimeofday, settimeofday,
+ * adjtime
+ */
+/*
+ * Modification history kernel/time.c
+ *
+ * 1993-09-02 Philip Gladstone
+ * Created file with time related functions from sched/core.c and adjtimex()
+ * 1993-10-08 Torsten Duwe
+ * adjtime interface update and CMOS clock write code
+ * 1995-08-13 Torsten Duwe
+ * kernel PLL updated to 1994-12-13 specs (rfc-1589)
+ * 1999-01-16 Ulrich Windl
+ * Introduced error checking for many cases in adjtimex().
+ * Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
+ * (Even though the technical memorandum forbids it)
+ * 2004-07-14 Christoph Lameter
+ * Added getnstimeofday to allow the posix timer functions to return
+ * with nanosecond accuracy
+ */
+
+#include <linux/export.h>
+#include <linux/timex.h>
+#include <linux/capability.h>
+#include <linux/timekeeper_internal.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/fs.h>
+#include <linux/math64.h>
+#include <linux/ptrace.h>
+
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+
+#include "timeconst.h"
+
+/*
+ * The timezone where the local system is located. Used as a default by some
+ * programs who obtain this value by using gettimeofday.
+ */
+struct timezone sys_tz;
+
+EXPORT_SYMBOL(sys_tz);
+
+#ifdef __ARCH_WANT_SYS_TIME
+
+/*
+ * sys_time() can be implemented in user-level using
+ * sys_gettimeofday(). Is this for backwards compatibility? If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ */
+SYSCALL_DEFINE1(time, time_t __user *, tloc)
+{
+ time_t i = get_seconds();
+
+ if (tloc) {
+ if (put_user(i,tloc))
+ return -EFAULT;
+ }
+ force_successful_syscall_return();
+ return i;
+}
+
+/*
+ * sys_stime() can be implemented in user-level using
+ * sys_settimeofday(). Is this for backwards compatibility? If so,
+ * why not move it into the appropriate arch directory (for those
+ * architectures that need it).
+ */
+
+SYSCALL_DEFINE1(stime, time_t __user *, tptr)
+{
+ struct timespec tv;
+ int err;
+
+ if (get_user(tv.tv_sec, tptr))
+ return -EFAULT;
+
+ tv.tv_nsec = 0;
+
+ err = security_settime(&tv, NULL);
+ if (err)
+ return err;
+
+ do_settimeofday(&tv);
+ return 0;
+}
+
+#endif /* __ARCH_WANT_SYS_TIME */
+
+SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
+ struct timezone __user *, tz)
+{
+ if (likely(tv != NULL)) {
+ struct timeval ktv;
+ do_gettimeofday(&ktv);
+ if (copy_to_user(tv, &ktv, sizeof(ktv)))
+ return -EFAULT;
+ }
+ if (unlikely(tz != NULL)) {
+ if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+/*
+ * Indicates if there is an offset between the system clock and the hardware
+ * clock/persistent clock/rtc.
+ */
+int persistent_clock_is_local;
+
+/*
+ * Adjust the time obtained from the CMOS to be UTC time instead of
+ * local time.
+ *
+ * This is ugly, but preferable to the alternatives. Otherwise we
+ * would either need to write a program to do it in /etc/rc (and risk
+ * confusion if the program gets run more than once; it would also be
+ * hard to make the program warp the clock precisely n hours) or
+ * compile in the timezone information into the kernel. Bad, bad....
+ *
+ * - TYT, 1992-01-01
+ *
+ * The best thing to do is to keep the CMOS clock in universal time (UTC)
+ * as real UNIX machines always do it. This avoids all headaches about
+ * daylight saving times and warping kernel clocks.
+ */
+static inline void warp_clock(void)
+{
+ if (sys_tz.tz_minuteswest != 0) {
+ struct timespec adjust;
+
+ persistent_clock_is_local = 1;
+ adjust.tv_sec = sys_tz.tz_minuteswest * 60;
+ adjust.tv_nsec = 0;
+ timekeeping_inject_offset(&adjust);
+ }
+}
+
+/*
+ * In case for some reason the CMOS clock has not already been running
+ * in UTC, but in some local time: The first time we set the timezone,
+ * we will warp the clock so that it is ticking UTC time instead of
+ * local time. Presumably, if someone is setting the timezone then we
+ * are running in an environment where the programs understand about
+ * timezones. This should be done at boot time in the /etc/rc script,
+ * as soon as possible, so that the clock can be set right. Otherwise,
+ * various programs will get confused when the clock gets warped.
+ */
+
+int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz)
+{
+ static int firsttime = 1;
+ int error = 0;
+
+ if (tv && !timespec_valid(tv))
+ return -EINVAL;
+
+ error = security_settime(tv, tz);
+ if (error)
+ return error;
+
+ if (tz) {
+ sys_tz = *tz;
+ update_vsyscall_tz();
+ if (firsttime) {
+ firsttime = 0;
+ if (!tv)
+ warp_clock();
+ }
+ }
+ if (tv)
+ return do_settimeofday(tv);
+ return 0;
+}
+
+SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
+ struct timezone __user *, tz)
+{
+ struct timeval user_tv;
+ struct timespec new_ts;
+ struct timezone new_tz;
+
+ if (tv) {
+ if (copy_from_user(&user_tv, tv, sizeof(*tv)))
+ return -EFAULT;
+ new_ts.tv_sec = user_tv.tv_sec;
+ new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
+ }
+ if (tz) {
+ if (copy_from_user(&new_tz, tz, sizeof(*tz)))
+ return -EFAULT;
+ }
+
+ return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+}
+
+SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
+{
+ struct timex txc; /* Local copy of parameter */
+ int ret;
+
+ /* Copy the user data space into the kernel copy
+ * structure. But bear in mind that the structures
+ * may change
+ */
+ if(copy_from_user(&txc, txc_p, sizeof(struct timex)))
+ return -EFAULT;
+ ret = do_adjtimex(&txc);
+ return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
+}
+
+/**
+ * current_fs_time - Return FS time
+ * @sb: Superblock.
+ *
+ * Return the current time truncated to the time granularity supported by
+ * the fs.
+ */
+struct timespec current_fs_time(struct super_block *sb)
+{
+ struct timespec now = current_kernel_time();
+ return timespec_trunc(now, sb->s_time_gran);
+}
+EXPORT_SYMBOL(current_fs_time);
+
+/*
+ * Convert jiffies to milliseconds and back.
+ *
+ * Avoid unnecessary multiplications/divisions in the
+ * two most common HZ cases:
+ */
+unsigned int jiffies_to_msecs(const unsigned long j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+ return (MSEC_PER_SEC / HZ) * j;
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+ return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
+#else
+# if BITS_PER_LONG == 32
+ return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+# else
+ return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+# endif
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_msecs);
+
+unsigned int jiffies_to_usecs(const unsigned long j)
+{
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+ return (USEC_PER_SEC / HZ) * j;
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+ return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
+#else
+# if BITS_PER_LONG == 32
+ return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
+# else
+ return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
+# endif
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_usecs);
+
+/**
+ * timespec_trunc - Truncate timespec to a granularity
+ * @t: Timespec
+ * @gran: Granularity in ns.
+ *
+ * Truncate a timespec to a granularity. gran must be smaller than a second.
+ * Always rounds down.
+ *
+ * This function should be only used for timestamps returned by
+ * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because
+ * it doesn't handle the better resolution of the latter.
+ */
+struct timespec timespec_trunc(struct timespec t, unsigned gran)
+{
+ /*
+ * Division is pretty slow so avoid it for common cases.
+ * Currently current_kernel_time() never returns better than
+ * jiffies resolution. Exploit that.
+ */
+ if (gran <= jiffies_to_usecs(1) * 1000) {
+ /* nothing */
+ } else if (gran == 1000000000) {
+ t.tv_nsec = 0;
+ } else {
+ t.tv_nsec -= t.tv_nsec % gran;
+ }
+ return t;
+}
+EXPORT_SYMBOL(timespec_trunc);
+
+/* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
+ * Assumes input in normal date format, i.e. 1980-12-31 23:59:59
+ * => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
+ *
+ * [For the Julian calendar (which was used in Russia before 1917,
+ * Britain & colonies before 1752, anywhere else before 1582,
+ * and is still in use by some communities) leave out the
+ * -year/100+year/400 terms, and add 10.]
+ *
+ * This algorithm was first published by Gauss (I think).
+ *
+ * WARNING: this function will overflow on 2106-02-07 06:28:16 on
+ * machines where long is 32-bit! (However, as time_t is signed, we
+ * will already get problems at other places on 2038-01-19 03:14:08)
+ */
+unsigned long
+mktime(const unsigned int year0, const unsigned int mon0,
+ const unsigned int day, const unsigned int hour,
+ const unsigned int min, const unsigned int sec)
+{
+ unsigned int mon = mon0, year = year0;
+
+ /* 1..12 -> 11,12,1..10 */
+ if (0 >= (int) (mon -= 2)) {
+ mon += 12; /* Puts Feb last since it has leap day */
+ year -= 1;
+ }
+
+ return ((((unsigned long)
+ (year/4 - year/100 + year/400 + 367*mon/12 + day) +
+ year*365 - 719499
+ )*24 + hour /* now have hours */
+ )*60 + min /* now have minutes */
+ )*60 + sec; /* finally seconds */
+}
+
+EXPORT_SYMBOL(mktime);
+
+/**
+ * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ *
+ * @ts: pointer to timespec variable to be set
+ * @sec: seconds to set
+ * @nsec: nanoseconds to set
+ *
+ * Set seconds and nanoseconds field of a timespec variable and
+ * normalize to the timespec storage format
+ *
+ * Note: The tv_nsec part is always in the range of
+ * 0 <= tv_nsec < NSEC_PER_SEC
+ * For negative values only the tv_sec field is negative !
+ */
+void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec)
+{
+ while (nsec >= NSEC_PER_SEC) {
+ /*
+ * The following asm() prevents the compiler from
+ * optimising this loop into a modulo operation. See
+ * also __iter_div_u64_rem() in include/linux/time.h
+ */
+ asm("" : "+rm"(nsec));
+ nsec -= NSEC_PER_SEC;
+ ++sec;
+ }
+ while (nsec < 0) {
+ asm("" : "+rm"(nsec));
+ nsec += NSEC_PER_SEC;
+ --sec;
+ }
+ ts->tv_sec = sec;
+ ts->tv_nsec = nsec;
+}
+EXPORT_SYMBOL(set_normalized_timespec);
+
+/**
+ * ns_to_timespec - Convert nanoseconds to timespec
+ * @nsec: the nanoseconds value to be converted
+ *
+ * Returns the timespec representation of the nsec parameter.
+ */
+struct timespec ns_to_timespec(const s64 nsec)
+{
+ struct timespec ts;
+ s32 rem;
+
+ if (!nsec)
+ return (struct timespec) {0, 0};
+
+ ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
+ if (unlikely(rem < 0)) {
+ ts.tv_sec--;
+ rem += NSEC_PER_SEC;
+ }
+ ts.tv_nsec = rem;
+
+ return ts;
+}
+EXPORT_SYMBOL(ns_to_timespec);
+
+/**
+ * ns_to_timeval - Convert nanoseconds to timeval
+ * @nsec: the nanoseconds value to be converted
+ *
+ * Returns the timeval representation of the nsec parameter.
+ */
+struct timeval ns_to_timeval(const s64 nsec)
+{
+ struct timespec ts = ns_to_timespec(nsec);
+ struct timeval tv;
+
+ tv.tv_sec = ts.tv_sec;
+ tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
+
+ return tv;
+}
+EXPORT_SYMBOL(ns_to_timeval);
+
+/*
+ * When we convert to jiffies then we interpret incoming values
+ * the following way:
+ *
+ * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
+ *
+ * - 'too large' values [that would result in larger than
+ * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
+ *
+ * - all other values are converted to jiffies by either multiplying
+ * the input value by a factor or dividing it with a factor
+ *
+ * We must also be careful about 32-bit overflows.
+ */
+unsigned long msecs_to_jiffies(const unsigned int m)
+{
+ /*
+ * Negative value, means infinite timeout:
+ */
+ if ((int)m < 0)
+ return MAX_JIFFY_OFFSET;
+
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+ /*
+ * HZ is equal to or smaller than 1000, and 1000 is a nice
+ * round multiple of HZ, divide with the factor between them,
+ * but round upwards:
+ */
+ return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
+#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+ /*
+ * HZ is larger than 1000, and HZ is a nice round multiple of
+ * 1000 - simply multiply with the factor between them.
+ *
+ * But first make sure the multiplication result cannot
+ * overflow:
+ */
+ if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+
+ return m * (HZ / MSEC_PER_SEC);
+#else
+ /*
+ * Generic case - multiply, round and divide. But first
+ * check that if we are doing a net multiplication, that
+ * we wouldn't overflow:
+ */
+ if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+
+ return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
+ >> MSEC_TO_HZ_SHR32;
+#endif
+}
+EXPORT_SYMBOL(msecs_to_jiffies);
+
+unsigned long usecs_to_jiffies(const unsigned int u)
+{
+ if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
+ return MAX_JIFFY_OFFSET;
+#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
+ return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
+#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
+ return u * (HZ / USEC_PER_SEC);
+#else
+ return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
+ >> USEC_TO_HZ_SHR32;
+#endif
+}
+EXPORT_SYMBOL(usecs_to_jiffies);
+
+/*
+ * The TICK_NSEC - 1 rounds up the value to the next resolution. Note
+ * that a remainder subtract here would not do the right thing as the
+ * resolution values don't fall on second boundries. I.e. the line:
+ * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ *
+ * Rather, we just shift the bits off the right.
+ *
+ * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
+ * value to a scaled second value.
+ */
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+ unsigned long sec = value->tv_sec;
+ long nsec = value->tv_nsec + TICK_NSEC - 1;
+
+ if (sec >= MAX_SEC_IN_JIFFIES){
+ sec = MAX_SEC_IN_JIFFIES;
+ nsec = 0;
+ }
+ return (((u64)sec * SEC_CONVERSION) +
+ (((u64)nsec * NSEC_CONVERSION) >>
+ (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+
+}
+EXPORT_SYMBOL(timespec_to_jiffies);
+
+void
+jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
+{
+ /*
+ * Convert jiffies to nanoseconds and separate with
+ * one divide.
+ */
+ u32 rem;
+ value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
+ NSEC_PER_SEC, &rem);
+ value->tv_nsec = rem;
+}
+EXPORT_SYMBOL(jiffies_to_timespec);
+
+/* Same for "timeval"
+ *
+ * Well, almost. The problem here is that the real system resolution is
+ * in nanoseconds and the value being converted is in micro seconds.
+ * Also for some machines (those that use HZ = 1024, in-particular),
+ * there is a LARGE error in the tick size in microseconds.
+
+ * The solution we use is to do the rounding AFTER we convert the
+ * microsecond part. Thus the USEC_ROUND, the bits to be shifted off.
+ * Instruction wise, this should cost only an additional add with carry
+ * instruction above the way it was done above.
+ */
+unsigned long
+timeval_to_jiffies(const struct timeval *value)
+{
+ unsigned long sec = value->tv_sec;
+ long usec = value->tv_usec;
+
+ if (sec >= MAX_SEC_IN_JIFFIES){
+ sec = MAX_SEC_IN_JIFFIES;
+ usec = 0;
+ }
+ return (((u64)sec * SEC_CONVERSION) +
+ (((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
+ (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+}
+EXPORT_SYMBOL(timeval_to_jiffies);
+
+void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value)
+{
+ /*
+ * Convert jiffies to nanoseconds and separate with
+ * one divide.
+ */
+ u32 rem;
+
+ value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
+ NSEC_PER_SEC, &rem);
+ value->tv_usec = rem / NSEC_PER_USEC;
+}
+EXPORT_SYMBOL(jiffies_to_timeval);
+
+/*
+ * Convert jiffies/jiffies_64 to clock_t and back.
+ */
+clock_t jiffies_to_clock_t(unsigned long x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+# if HZ < USER_HZ
+ return x * (USER_HZ / HZ);
+# else
+ return x / (HZ / USER_HZ);
+# endif
+#else
+ return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ);
+#endif
+}
+EXPORT_SYMBOL(jiffies_to_clock_t);
+
+unsigned long clock_t_to_jiffies(unsigned long x)
+{
+#if (HZ % USER_HZ)==0
+ if (x >= ~0UL / (HZ / USER_HZ))
+ return ~0UL;
+ return x * (HZ / USER_HZ);
+#else
+ /* Don't worry about loss of precision here .. */
+ if (x >= ~0UL / HZ * USER_HZ)
+ return ~0UL;
+
+ /* .. but do try to contain it here */
+ return div_u64((u64)x * HZ, USER_HZ);
+#endif
+}
+EXPORT_SYMBOL(clock_t_to_jiffies);
+
+u64 jiffies_64_to_clock_t(u64 x)
+{
+#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
+# if HZ < USER_HZ
+ x = div_u64(x * USER_HZ, HZ);
+# elif HZ > USER_HZ
+ x = div_u64(x, HZ / USER_HZ);
+# else
+ /* Nothing to do */
+# endif
+#else
+ /*
+ * There are better ways that don't overflow early,
+ * but even this doesn't overflow in hundreds of years
+ * in 64 bits, so..
+ */
+ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ));
+#endif
+ return x;
+}
+EXPORT_SYMBOL(jiffies_64_to_clock_t);
+
+u64 nsec_to_clock_t(u64 x)
+{
+#if (NSEC_PER_SEC % USER_HZ) == 0
+ return div_u64(x, NSEC_PER_SEC / USER_HZ);
+#elif (USER_HZ % 512) == 0
+ return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
+#else
+ /*
+ * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
+ * overflow after 64.99 years.
+ * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
+ */
+ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
+#endif
+}
+
+/**
+ * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
+ *
+ * @n: nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+u64 nsecs_to_jiffies64(u64 n)
+{
+#if (NSEC_PER_SEC % HZ) == 0
+ /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
+ return div_u64(n, NSEC_PER_SEC / HZ);
+#elif (HZ % 512) == 0
+ /* overflow after 292 years if HZ = 1024 */
+ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
+#else
+ /*
+ * Generic case - optimized for cases where HZ is a multiple of 3.
+ * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
+ */
+ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
+#endif
+}
+
+/**
+ * nsecs_to_jiffies - Convert nsecs in u64 to jiffies
+ *
+ * @n: nsecs in u64
+ *
+ * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
+ * And this doesn't return MAX_JIFFY_OFFSET since this function is designed
+ * for scheduler, not for use in device drivers to calculate timeout value.
+ *
+ * note:
+ * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
+ * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
+ */
+unsigned long nsecs_to_jiffies(u64 n)
+{
+ return (unsigned long)nsecs_to_jiffies64(n);
+}
+
+/*
+ * Add two timespec values and do a safety check for overflow.
+ * It's assumed that both values are valid (>= 0)
+ */
+struct timespec timespec_add_safe(const struct timespec lhs,
+ const struct timespec rhs)
+{
+ struct timespec res;
+
+ set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
+ lhs.tv_nsec + rhs.tv_nsec);
+
+ if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
+ res.tv_sec = TIME_T_MAX;
+
+ return res;
+}
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
new file mode 100644
index 000000000000..511bdf2cafda
--- /dev/null
+++ b/kernel/time/timeconst.bc
@@ -0,0 +1,108 @@
+scale=0
+
+define gcd(a,b) {
+ auto t;
+ while (b) {
+ t = b;
+ b = a % b;
+ a = t;
+ }
+ return a;
+}
+
+/* Division by reciprocal multiplication. */
+define fmul(b,n,d) {
+ return (2^b*n+d-1)/d;
+}
+
+/* Adjustment factor when a ceiling value is used. Use as:
+ (imul * n) + (fmulxx * n + fadjxx) >> xx) */
+define fadj(b,n,d) {
+ auto v;
+ d = d/gcd(n,d);
+ v = 2^b*(d-1)/d;
+ return v;
+}
+
+/* Compute the appropriate mul/adj values as well as a shift count,
+ which brings the mul value into the range 2^b-1 <= x < 2^b. Such
+ a shift value will be correct in the signed integer range and off
+ by at most one in the upper half of the unsigned range. */
+define fmuls(b,n,d) {
+ auto s, m;
+ for (s = 0; 1; s++) {
+ m = fmul(s,n,d);
+ if (m >= 2^(b-1))
+ return s;
+ }
+ return 0;
+}
+
+define timeconst(hz) {
+ print "/* Automatically generated by kernel/timeconst.bc */\n"
+ print "/* Time conversion constants for HZ == ", hz, " */\n"
+ print "\n"
+
+ print "#ifndef KERNEL_TIMECONST_H\n"
+ print "#define KERNEL_TIMECONST_H\n\n"
+
+ print "#include <linux/param.h>\n"
+ print "#include <linux/types.h>\n\n"
+
+ print "#if HZ != ", hz, "\n"
+ print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n"
+ print "#endif\n\n"
+
+ if (hz < 2) {
+ print "#error Totally bogus HZ value!\n"
+ } else {
+ s=fmuls(32,1000,hz)
+ obase=16
+ print "#define HZ_TO_MSEC_MUL32\tU64_C(0x", fmul(s,1000,hz), ")\n"
+ print "#define HZ_TO_MSEC_ADJ32\tU64_C(0x", fadj(s,1000,hz), ")\n"
+ obase=10
+ print "#define HZ_TO_MSEC_SHR32\t", s, "\n"
+
+ s=fmuls(32,hz,1000)
+ obase=16
+ print "#define MSEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000), ")\n"
+ print "#define MSEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000), ")\n"
+ obase=10
+ print "#define MSEC_TO_HZ_SHR32\t", s, "\n"
+
+ obase=10
+ cd=gcd(hz,1000)
+ print "#define HZ_TO_MSEC_NUM\t\t", 1000/cd, "\n"
+ print "#define HZ_TO_MSEC_DEN\t\t", hz/cd, "\n"
+ print "#define MSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+ print "#define MSEC_TO_HZ_DEN\t\t", 1000/cd, "\n"
+ print "\n"
+
+ s=fmuls(32,1000000,hz)
+ obase=16
+ print "#define HZ_TO_USEC_MUL32\tU64_C(0x", fmul(s,1000000,hz), ")\n"
+ print "#define HZ_TO_USEC_ADJ32\tU64_C(0x", fadj(s,1000000,hz), ")\n"
+ obase=10
+ print "#define HZ_TO_USEC_SHR32\t", s, "\n"
+
+ s=fmuls(32,hz,1000000)
+ obase=16
+ print "#define USEC_TO_HZ_MUL32\tU64_C(0x", fmul(s,hz,1000000), ")\n"
+ print "#define USEC_TO_HZ_ADJ32\tU64_C(0x", fadj(s,hz,1000000), ")\n"
+ obase=10
+ print "#define USEC_TO_HZ_SHR32\t", s, "\n"
+
+ obase=10
+ cd=gcd(hz,1000000)
+ print "#define HZ_TO_USEC_NUM\t\t", 1000000/cd, "\n"
+ print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n"
+ print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+ print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n"
+ print "\n"
+
+ print "#endif /* KERNEL_TIMECONST_H */\n"
+ }
+ halt
+}
+
+timeconst(hz)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
new file mode 100644
index 000000000000..3bb01a323b2a
--- /dev/null
+++ b/kernel/time/timer.c
@@ -0,0 +1,1734 @@
+/*
+ * linux/kernel/timer.c
+ *
+ * Kernel internal timers
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better.
+ *
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
+ * serialize accesses to xtime/lost_ticks).
+ * Copyright (C) 1998 Andrea Arcangeli
+ * 1999-03-10 Improved NTP compatibility by Ulrich Windl
+ * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love
+ * 2000-10-05 Implemented scalable SMP per-CPU timer handling.
+ * Copyright (C) 2000, 2001, 2002 Ingo Molnar
+ * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/export.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pid_namespace.h>
+#include <linux/notifier.h>
+#include <linux/thread_info.h>
+#include <linux/time.h>
+#include <linux/jiffies.h>
+#include <linux/posix-timers.h>
+#include <linux/cpu.h>
+#include <linux/syscalls.h>
+#include <linux/delay.h>
+#include <linux/tick.h>
+#include <linux/kallsyms.h>
+#include <linux/irq_work.h>
+#include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/slab.h>
+#include <linux/compat.h>
+
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/div64.h>
+#include <asm/timex.h>
+#include <asm/io.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/timer.h>
+
+__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+
+EXPORT_SYMBOL(jiffies_64);
+
+/*
+ * per-CPU timer vector definitions:
+ */
+#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6)
+#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8)
+#define TVN_SIZE (1 << TVN_BITS)
+#define TVR_SIZE (1 << TVR_BITS)
+#define TVN_MASK (TVN_SIZE - 1)
+#define TVR_MASK (TVR_SIZE - 1)
+#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1))
+
+struct tvec {
+ struct list_head vec[TVN_SIZE];
+};
+
+struct tvec_root {
+ struct list_head vec[TVR_SIZE];
+};
+
+struct tvec_base {
+ spinlock_t lock;
+ struct timer_list *running_timer;
+ unsigned long timer_jiffies;
+ unsigned long next_timer;
+ unsigned long active_timers;
+ unsigned long all_timers;
+ struct tvec_root tv1;
+ struct tvec tv2;
+ struct tvec tv3;
+ struct tvec tv4;
+ struct tvec tv5;
+} ____cacheline_aligned;
+
+struct tvec_base boot_tvec_bases;
+EXPORT_SYMBOL(boot_tvec_bases);
+static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
+
+/* Functions below help us manage 'deferrable' flag */
+static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
+{
+ return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE);
+}
+
+static inline unsigned int tbase_get_irqsafe(struct tvec_base *base)
+{
+ return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE);
+}
+
+static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+{
+ return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK));
+}
+
+static inline void
+timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
+{
+ unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK;
+
+ timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags);
+}
+
+static unsigned long round_jiffies_common(unsigned long j, int cpu,
+ bool force_up)
+{
+ int rem;
+ unsigned long original = j;
+
+ /*
+ * We don't want all cpus firing their timers at once hitting the
+ * same lock or cachelines, so we skew each extra cpu with an extra
+ * 3 jiffies. This 3 jiffies came originally from the mm/ code which
+ * already did this.
+ * The skew is done by adding 3*cpunr, then round, then subtract this
+ * extra offset again.
+ */
+ j += cpu * 3;
+
+ rem = j % HZ;
+
+ /*
+ * If the target jiffie is just after a whole second (which can happen
+ * due to delays of the timer irq, long irq off times etc etc) then
+ * we should round down to the whole second, not up. Use 1/4th second
+ * as cutoff for this rounding as an extreme upper bound for this.
+ * But never round down if @force_up is set.
+ */
+ if (rem < HZ/4 && !force_up) /* round down */
+ j = j - rem;
+ else /* round up */
+ j = j - rem + HZ;
+
+ /* now that we have rounded, subtract the extra skew again */
+ j -= cpu * 3;
+
+ /*
+ * Make sure j is still in the future. Otherwise return the
+ * unmodified value.
+ */
+ return time_is_after_jiffies(j) ? j : original;
+}
+
+/**
+ * __round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies(unsigned long j, int cpu)
+{
+ return round_jiffies_common(j, cpu, false);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies);
+
+/**
+ * __round_jiffies_relative - function to round jiffies to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies_relative() rounds a time delta in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies_relative(unsigned long j, int cpu)
+{
+ unsigned long j0 = jiffies;
+
+ /* Use j0 because jiffies might change while we run */
+ return round_jiffies_common(j + j0, cpu, false) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_relative);
+
+/**
+ * round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long round_jiffies(unsigned long j)
+{
+ return round_jiffies_common(j, raw_smp_processor_id(), false);
+}
+EXPORT_SYMBOL_GPL(round_jiffies);
+
+/**
+ * round_jiffies_relative - function to round jiffies to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * round_jiffies_relative() rounds a time delta in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long round_jiffies_relative(unsigned long j)
+{
+ return __round_jiffies_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_relative);
+
+/**
+ * __round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies() except that it will never
+ * round down. This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up(unsigned long j, int cpu)
+{
+ return round_jiffies_common(j, cpu, true);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up);
+
+/**
+ * __round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies_relative() except that it will never
+ * round down. This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
+{
+ unsigned long j0 = jiffies;
+
+ /* Use j0 because jiffies might change while we run */
+ return round_jiffies_common(j + j0, cpu, true) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
+
+/**
+ * round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies() except that it will never
+ * round down. This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up(unsigned long j)
+{
+ return round_jiffies_common(j, raw_smp_processor_id(), true);
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up);
+
+/**
+ * round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies_relative() except that it will never
+ * round down. This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up_relative(unsigned long j)
+{
+ return __round_jiffies_up_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
+
+/**
+ * set_timer_slack - set the allowed slack for a timer
+ * @timer: the timer to be modified
+ * @slack_hz: the amount of time (in jiffies) allowed for rounding
+ *
+ * Set the amount of time, in jiffies, that a certain timer has
+ * in terms of slack. By setting this value, the timer subsystem
+ * will schedule the actual timer somewhere between
+ * the time mod_timer() asks for, and that time plus the slack.
+ *
+ * By setting the slack to -1, a percentage of the delay is used
+ * instead.
+ */
+void set_timer_slack(struct timer_list *timer, int slack_hz)
+{
+ timer->slack = slack_hz;
+}
+EXPORT_SYMBOL_GPL(set_timer_slack);
+
+/*
+ * If the list is empty, catch up ->timer_jiffies to the current time.
+ * The caller must hold the tvec_base lock. Returns true if the list
+ * was empty and therefore ->timer_jiffies was updated.
+ */
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+ if (!base->all_timers) {
+ base->timer_jiffies = jiffies;
+ return true;
+ }
+ return false;
+}
+
+static void
+__internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+{
+ unsigned long expires = timer->expires;
+ unsigned long idx = expires - base->timer_jiffies;
+ struct list_head *vec;
+
+ if (idx < TVR_SIZE) {
+ int i = expires & TVR_MASK;
+ vec = base->tv1.vec + i;
+ } else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
+ int i = (expires >> TVR_BITS) & TVN_MASK;
+ vec = base->tv2.vec + i;
+ } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
+ int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
+ vec = base->tv3.vec + i;
+ } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
+ int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
+ vec = base->tv4.vec + i;
+ } else if ((signed long) idx < 0) {
+ /*
+ * Can happen if you add a timer with expires == jiffies,
+ * or you set a timer to go off in the past
+ */
+ vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
+ } else {
+ int i;
+ /* If the timeout is larger than MAX_TVAL (on 64-bit
+ * architectures or with CONFIG_BASE_SMALL=1) then we
+ * use the maximum timeout.
+ */
+ if (idx > MAX_TVAL) {
+ idx = MAX_TVAL;
+ expires = idx + base->timer_jiffies;
+ }
+ i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
+ vec = base->tv5.vec + i;
+ }
+ /*
+ * Timers are FIFO:
+ */
+ list_add_tail(&timer->entry, vec);
+}
+
+static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
+{
+ (void)catchup_timer_jiffies(base);
+ __internal_add_timer(base, timer);
+ /*
+ * Update base->active_timers and base->next_timer
+ */
+ if (!tbase_get_deferrable(timer->base)) {
+ if (!base->active_timers++ ||
+ time_before(timer->expires, base->next_timer))
+ base->next_timer = timer->expires;
+ }
+ base->all_timers++;
+}
+
+#ifdef CONFIG_TIMER_STATS
+void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
+{
+ if (timer->start_site)
+ return;
+
+ timer->start_site = addr;
+ memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
+ timer->start_pid = current->pid;
+}
+
+static void timer_stats_account_timer(struct timer_list *timer)
+{
+ unsigned int flag = 0;
+
+ if (likely(!timer->start_site))
+ return;
+ if (unlikely(tbase_get_deferrable(timer->base)))
+ flag |= TIMER_STATS_FLAG_DEFERRABLE;
+
+ timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
+ timer->function, timer->start_comm, flag);
+}
+
+#else
+static void timer_stats_account_timer(struct timer_list *timer) {}
+#endif
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+
+static struct debug_obj_descr timer_debug_descr;
+
+static void *timer_debug_hint(void *addr)
+{
+ return ((struct timer_list *) addr)->function;
+}
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int timer_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct timer_list *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ del_timer_sync(timer);
+ debug_object_init(timer, &timer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/* Stub timer callback for improperly used timers. */
+static void stub_timer(unsigned long data)
+{
+ WARN_ON(1);
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int timer_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct timer_list *timer = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. The timer was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ if (timer->entry.next == NULL &&
+ timer->entry.prev == TIMER_ENTRY_STATIC) {
+ debug_object_init(timer, &timer_debug_descr);
+ debug_object_activate(timer, &timer_debug_descr);
+ return 0;
+ } else {
+ setup_timer(timer, stub_timer, 0);
+ return 1;
+ }
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int timer_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct timer_list *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ del_timer_sync(timer);
+ debug_object_free(timer, &timer_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_assert_init is called when:
+ * - an untracked/uninit-ed object is found
+ */
+static int timer_fixup_assert_init(void *addr, enum debug_obj_state state)
+{
+ struct timer_list *timer = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_NOTAVAILABLE:
+ if (timer->entry.prev == TIMER_ENTRY_STATIC) {
+ /*
+ * This is not really a fixup. The timer was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ debug_object_init(timer, &timer_debug_descr);
+ return 0;
+ } else {
+ setup_timer(timer, stub_timer, 0);
+ return 1;
+ }
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr timer_debug_descr = {
+ .name = "timer_list",
+ .debug_hint = timer_debug_hint,
+ .fixup_init = timer_fixup_init,
+ .fixup_activate = timer_fixup_activate,
+ .fixup_free = timer_fixup_free,
+ .fixup_assert_init = timer_fixup_assert_init,
+};
+
+static inline void debug_timer_init(struct timer_list *timer)
+{
+ debug_object_init(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_activate(struct timer_list *timer)
+{
+ debug_object_activate(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_deactivate(struct timer_list *timer)
+{
+ debug_object_deactivate(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_free(struct timer_list *timer)
+{
+ debug_object_free(timer, &timer_debug_descr);
+}
+
+static inline void debug_timer_assert_init(struct timer_list *timer)
+{
+ debug_object_assert_init(timer, &timer_debug_descr);
+}
+
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key);
+
+void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
+{
+ debug_object_init_on_stack(timer, &timer_debug_descr);
+ do_init_timer(timer, flags, name, key);
+}
+EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
+
+void destroy_timer_on_stack(struct timer_list *timer)
+{
+ debug_object_free(timer, &timer_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_timer_on_stack);
+
+#else
+static inline void debug_timer_init(struct timer_list *timer) { }
+static inline void debug_timer_activate(struct timer_list *timer) { }
+static inline void debug_timer_deactivate(struct timer_list *timer) { }
+static inline void debug_timer_assert_init(struct timer_list *timer) { }
+#endif
+
+static inline void debug_init(struct timer_list *timer)
+{
+ debug_timer_init(timer);
+ trace_timer_init(timer);
+}
+
+static inline void
+debug_activate(struct timer_list *timer, unsigned long expires)
+{
+ debug_timer_activate(timer);
+ trace_timer_start(timer, expires);
+}
+
+static inline void debug_deactivate(struct timer_list *timer)
+{
+ debug_timer_deactivate(timer);
+ trace_timer_cancel(timer);
+}
+
+static inline void debug_assert_init(struct timer_list *timer)
+{
+ debug_timer_assert_init(timer);
+}
+
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
+{
+ struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+
+ timer->entry.next = NULL;
+ timer->base = (void *)((unsigned long)base | flags);
+ timer->slack = -1;
+#ifdef CONFIG_TIMER_STATS
+ timer->start_site = NULL;
+ timer->start_pid = -1;
+ memset(timer->start_comm, 0, TASK_COMM_LEN);
+#endif
+ lockdep_init_map(&timer->lockdep_map, name, key, 0);
+}
+
+/**
+ * init_timer_key - initialize a timer
+ * @timer: the timer to be initialized
+ * @flags: timer flags
+ * @name: name of the timer
+ * @key: lockdep class key of the fake lock used for tracking timer
+ * sync lock dependencies
+ *
+ * init_timer_key() must be done to a timer prior calling *any* of the
+ * other timer functions.
+ */
+void init_timer_key(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
+{
+ debug_init(timer);
+ do_init_timer(timer, flags, name, key);
+}
+EXPORT_SYMBOL(init_timer_key);
+
+static inline void detach_timer(struct timer_list *timer, bool clear_pending)
+{
+ struct list_head *entry = &timer->entry;
+
+ debug_deactivate(timer);
+
+ __list_del(entry->prev, entry->next);
+ if (clear_pending)
+ entry->next = NULL;
+ entry->prev = LIST_POISON2;
+}
+
+static inline void
+detach_expired_timer(struct timer_list *timer, struct tvec_base *base)
+{
+ detach_timer(timer, true);
+ if (!tbase_get_deferrable(timer->base))
+ base->active_timers--;
+ base->all_timers--;
+ (void)catchup_timer_jiffies(base);
+}
+
+static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
+ bool clear_pending)
+{
+ if (!timer_pending(timer))
+ return 0;
+
+ detach_timer(timer, clear_pending);
+ if (!tbase_get_deferrable(timer->base)) {
+ base->active_timers--;
+ if (timer->expires == base->next_timer)
+ base->next_timer = base->timer_jiffies;
+ }
+ base->all_timers--;
+ (void)catchup_timer_jiffies(base);
+ return 1;
+}
+
+/*
+ * We are using hashed locking: holding per_cpu(tvec_bases).lock
+ * means that all timers which are tied to this base via timer->base are
+ * locked, and the base itself is locked too.
+ *
+ * So __run_timers/migrate_timers can safely modify all timers which could
+ * be found on ->tvX lists.
+ *
+ * When the timer's base is locked, and the timer removed from list, it is
+ * possible to set timer->base = NULL and drop the lock: the timer remains
+ * locked.
+ */
+static struct tvec_base *lock_timer_base(struct timer_list *timer,
+ unsigned long *flags)
+ __acquires(timer->base->lock)
+{
+ struct tvec_base *base;
+
+ for (;;) {
+ struct tvec_base *prelock_base = timer->base;
+ base = tbase_get_base(prelock_base);
+ if (likely(base != NULL)) {
+ spin_lock_irqsave(&base->lock, *flags);
+ if (likely(prelock_base == timer->base))
+ return base;
+ /* The timer has migrated to another CPU */
+ spin_unlock_irqrestore(&base->lock, *flags);
+ }
+ cpu_relax();
+ }
+}
+
+static inline int
+__mod_timer(struct timer_list *timer, unsigned long expires,
+ bool pending_only, int pinned)
+{
+ struct tvec_base *base, *new_base;
+ unsigned long flags;
+ int ret = 0 , cpu;
+
+ timer_stats_timer_set_start_info(timer);
+ BUG_ON(!timer->function);
+
+ base = lock_timer_base(timer, &flags);
+
+ ret = detach_if_pending(timer, base, false);
+ if (!ret && pending_only)
+ goto out_unlock;
+
+ debug_activate(timer, expires);
+
+ cpu = get_nohz_timer_target(pinned);
+ new_base = per_cpu(tvec_bases, cpu);
+
+ if (base != new_base) {
+ /*
+ * We are trying to schedule the timer on the local CPU.
+ * However we can't change timer's base while it is running,
+ * otherwise del_timer_sync() can't detect that the timer's
+ * handler yet has not finished. This also guarantees that
+ * the timer is serialized wrt itself.
+ */
+ if (likely(base->running_timer != timer)) {
+ /* See the comment in lock_timer_base() */
+ timer_set_base(timer, NULL);
+ spin_unlock(&base->lock);
+ base = new_base;
+ spin_lock(&base->lock);
+ timer_set_base(timer, base);
+ }
+ }
+
+ timer->expires = expires;
+ internal_add_timer(base, timer);
+
+out_unlock:
+ spin_unlock_irqrestore(&base->lock, flags);
+
+ return ret;
+}
+
+/**
+ * mod_timer_pending - modify a pending timer's timeout
+ * @timer: the pending timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer_pending() is the same for pending timers as mod_timer(),
+ * but will not re-activate and modify already deleted timers.
+ *
+ * It is useful for unserialized use of timers.
+ */
+int mod_timer_pending(struct timer_list *timer, unsigned long expires)
+{
+ return __mod_timer(timer, expires, true, TIMER_NOT_PINNED);
+}
+EXPORT_SYMBOL(mod_timer_pending);
+
+/*
+ * Decide where to put the timer while taking the slack into account
+ *
+ * Algorithm:
+ * 1) calculate the maximum (absolute) time
+ * 2) calculate the highest bit where the expires and new max are different
+ * 3) use this bit to make a mask
+ * 4) use the bitmask to round down the maximum time, so that all last
+ * bits are zeros
+ */
+static inline
+unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
+{
+ unsigned long expires_limit, mask;
+ int bit;
+
+ if (timer->slack >= 0) {
+ expires_limit = expires + timer->slack;
+ } else {
+ long delta = expires - jiffies;
+
+ if (delta < 256)
+ return expires;
+
+ expires_limit = expires + delta / 256;
+ }
+ mask = expires ^ expires_limit;
+ if (mask == 0)
+ return expires;
+
+ bit = find_last_bit(&mask, BITS_PER_LONG);
+
+ mask = (1UL << bit) - 1;
+
+ expires_limit = expires_limit & ~(mask);
+
+ return expires_limit;
+}
+
+/**
+ * mod_timer - modify a timer's timeout
+ * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer() is a more efficient way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ *
+ * mod_timer(timer, expires) is equivalent to:
+ *
+ * del_timer(timer); timer->expires = expires; add_timer(timer);
+ *
+ * Note that if there are multiple unserialized concurrent users of the
+ * same timer, then mod_timer() is the only safe way to modify the timeout,
+ * since add_timer() cannot modify an already running timer.
+ *
+ * The function returns whether it has modified a pending timer or not.
+ * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
+ * active timer returns 1.)
+ */
+int mod_timer(struct timer_list *timer, unsigned long expires)
+{
+ expires = apply_slack(timer, expires);
+
+ /*
+ * This is a common optimization triggered by the
+ * networking code - if the timer is re-modified
+ * to be the same thing then just return:
+ */
+ if (timer_pending(timer) && timer->expires == expires)
+ return 1;
+
+ return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
+}
+EXPORT_SYMBOL(mod_timer);
+
+/**
+ * mod_timer_pinned - modify a timer's timeout
+ * @timer: the timer to be modified
+ * @expires: new timeout in jiffies
+ *
+ * mod_timer_pinned() is a way to update the expire field of an
+ * active timer (if the timer is inactive it will be activated)
+ * and to ensure that the timer is scheduled on the current CPU.
+ *
+ * Note that this does not prevent the timer from being migrated
+ * when the current CPU goes offline. If this is a problem for
+ * you, use CPU-hotplug notifiers to handle it correctly, for
+ * example, cancelling the timer when the corresponding CPU goes
+ * offline.
+ *
+ * mod_timer_pinned(timer, expires) is equivalent to:
+ *
+ * del_timer(timer); timer->expires = expires; add_timer(timer);
+ */
+int mod_timer_pinned(struct timer_list *timer, unsigned long expires)
+{
+ if (timer->expires == expires && timer_pending(timer))
+ return 1;
+
+ return __mod_timer(timer, expires, false, TIMER_PINNED);
+}
+EXPORT_SYMBOL(mod_timer_pinned);
+
+/**
+ * add_timer - start a timer
+ * @timer: the timer to be added
+ *
+ * The kernel will do a ->function(->data) callback from the
+ * timer interrupt at the ->expires point in the future. The
+ * current time is 'jiffies'.
+ *
+ * The timer's ->expires, ->function (and if the handler uses it, ->data)
+ * fields must be set prior calling this function.
+ *
+ * Timers with an ->expires field in the past will be executed in the next
+ * timer tick.
+ */
+void add_timer(struct timer_list *timer)
+{
+ BUG_ON(timer_pending(timer));
+ mod_timer(timer, timer->expires);
+}
+EXPORT_SYMBOL(add_timer);
+
+/**
+ * add_timer_on - start a timer on a particular CPU
+ * @timer: the timer to be added
+ * @cpu: the CPU to start it on
+ *
+ * This is not very scalable on SMP. Double adds are not possible.
+ */
+void add_timer_on(struct timer_list *timer, int cpu)
+{
+ struct tvec_base *base = per_cpu(tvec_bases, cpu);
+ unsigned long flags;
+
+ timer_stats_timer_set_start_info(timer);
+ BUG_ON(timer_pending(timer) || !timer->function);
+ spin_lock_irqsave(&base->lock, flags);
+ timer_set_base(timer, base);
+ debug_activate(timer, timer->expires);
+ internal_add_timer(base, timer);
+ /*
+ * Check whether the other CPU is in dynticks mode and needs
+ * to be triggered to reevaluate the timer wheel.
+ * We are protected against the other CPU fiddling
+ * with the timer by holding the timer base lock. This also
+ * makes sure that a CPU on the way to stop its tick can not
+ * evaluate the timer wheel.
+ *
+ * Spare the IPI for deferrable timers on idle targets though.
+ * The next busy ticks will take care of it. Except full dynticks
+ * require special care against races with idle_cpu(), lets deal
+ * with that later.
+ */
+ if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu))
+ wake_up_nohz_cpu(cpu);
+
+ spin_unlock_irqrestore(&base->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_timer_on);
+
+/**
+ * del_timer - deactive a timer.
+ * @timer: the timer to be deactivated
+ *
+ * del_timer() deactivates a timer - this works on both active and inactive
+ * timers.
+ *
+ * The function returns whether it has deactivated a pending timer or not.
+ * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
+ * active timer returns 1.)
+ */
+int del_timer(struct timer_list *timer)
+{
+ struct tvec_base *base;
+ unsigned long flags;
+ int ret = 0;
+
+ debug_assert_init(timer);
+
+ timer_stats_timer_clear_start_info(timer);
+ if (timer_pending(timer)) {
+ base = lock_timer_base(timer, &flags);
+ ret = detach_if_pending(timer, base, true);
+ spin_unlock_irqrestore(&base->lock, flags);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(del_timer);
+
+/**
+ * try_to_del_timer_sync - Try to deactivate a timer
+ * @timer: timer do del
+ *
+ * This function tries to deactivate a timer. Upon successful (ret >= 0)
+ * exit the timer is not queued and the handler is not running on any CPU.
+ */
+int try_to_del_timer_sync(struct timer_list *timer)
+{
+ struct tvec_base *base;
+ unsigned long flags;
+ int ret = -1;
+
+ debug_assert_init(timer);
+
+ base = lock_timer_base(timer, &flags);
+
+ if (base->running_timer != timer) {
+ timer_stats_timer_clear_start_info(timer);
+ ret = detach_if_pending(timer, base, true);
+ }
+ spin_unlock_irqrestore(&base->lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL(try_to_del_timer_sync);
+
+#ifdef CONFIG_SMP
+/**
+ * del_timer_sync - deactivate a timer and wait for the handler to finish.
+ * @timer: the timer to be deactivated
+ *
+ * This function only differs from del_timer() on SMP: besides deactivating
+ * the timer it also makes sure the handler has finished executing on other
+ * CPUs.
+ *
+ * Synchronization rules: Callers must prevent restarting of the timer,
+ * otherwise this function is meaningless. It must not be called from
+ * interrupt contexts unless the timer is an irqsafe one. The caller must
+ * not hold locks which would prevent completion of the timer's
+ * handler. The timer's handler must not call add_timer_on(). Upon exit the
+ * timer is not queued and the handler is not running on any CPU.
+ *
+ * Note: For !irqsafe timers, you must not hold locks that are held in
+ * interrupt context while calling this function. Even if the lock has
+ * nothing to do with the timer in question. Here's why:
+ *
+ * CPU0 CPU1
+ * ---- ----
+ * <SOFTIRQ>
+ * call_timer_fn();
+ * base->running_timer = mytimer;
+ * spin_lock_irq(somelock);
+ * <IRQ>
+ * spin_lock(somelock);
+ * del_timer_sync(mytimer);
+ * while (base->running_timer == mytimer);
+ *
+ * Now del_timer_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but
+ * it has interrupted the softirq that CPU0 is waiting to finish.
+ *
+ * The function returns whether it has deactivated a pending timer or not.
+ */
+int del_timer_sync(struct timer_list *timer)
+{
+#ifdef CONFIG_LOCKDEP
+ unsigned long flags;
+
+ /*
+ * If lockdep gives a backtrace here, please reference
+ * the synchronization rules above.
+ */
+ local_irq_save(flags);
+ lock_map_acquire(&timer->lockdep_map);
+ lock_map_release(&timer->lockdep_map);
+ local_irq_restore(flags);
+#endif
+ /*
+ * don't use it in hardirq context, because it
+ * could lead to deadlock.
+ */
+ WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base));
+ for (;;) {
+ int ret = try_to_del_timer_sync(timer);
+ if (ret >= 0)
+ return ret;
+ cpu_relax();
+ }
+}
+EXPORT_SYMBOL(del_timer_sync);
+#endif
+
+static int cascade(struct tvec_base *base, struct tvec *tv, int index)
+{
+ /* cascade all the timers from tv up one level */
+ struct timer_list *timer, *tmp;
+ struct list_head tv_list;
+
+ list_replace_init(tv->vec + index, &tv_list);
+
+ /*
+ * We are removing _all_ timers from the list, so we
+ * don't have to detach them individually.
+ */
+ list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
+ BUG_ON(tbase_get_base(timer->base) != base);
+ /* No accounting, while moving them */
+ __internal_add_timer(base, timer);
+ }
+
+ return index;
+}
+
+static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
+ unsigned long data)
+{
+ int count = preempt_count();
+
+#ifdef CONFIG_LOCKDEP
+ /*
+ * It is permissible to free the timer from inside the
+ * function that is called from it, this we need to take into
+ * account for lockdep too. To avoid bogus "held lock freed"
+ * warnings as well as problems when looking into
+ * timer->lockdep_map, make a copy and use that here.
+ */
+ struct lockdep_map lockdep_map;
+
+ lockdep_copy_map(&lockdep_map, &timer->lockdep_map);
+#endif
+ /*
+ * Couple the lock chain with the lock chain at
+ * del_timer_sync() by acquiring the lock_map around the fn()
+ * call here and in del_timer_sync().
+ */
+ lock_map_acquire(&lockdep_map);
+
+ trace_timer_expire_entry(timer);
+ fn(data);
+ trace_timer_expire_exit(timer);
+
+ lock_map_release(&lockdep_map);
+
+ if (count != preempt_count()) {
+ WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
+ fn, count, preempt_count());
+ /*
+ * Restore the preempt count. That gives us a decent
+ * chance to survive and extract information. If the
+ * callback kept a lock held, bad luck, but not worse
+ * than the BUG() we had.
+ */
+ preempt_count_set(count);
+ }
+}
+
+#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
+
+/**
+ * __run_timers - run all expired timers (if any) on this CPU.
+ * @base: the timer vector to be processed.
+ *
+ * This function cascades all vectors and executes all expired timer
+ * vectors.
+ */
+static inline void __run_timers(struct tvec_base *base)
+{
+ struct timer_list *timer;
+
+ spin_lock_irq(&base->lock);
+ if (catchup_timer_jiffies(base)) {
+ spin_unlock_irq(&base->lock);
+ return;
+ }
+ while (time_after_eq(jiffies, base->timer_jiffies)) {
+ struct list_head work_list;
+ struct list_head *head = &work_list;
+ int index = base->timer_jiffies & TVR_MASK;
+
+ /*
+ * Cascade timers:
+ */
+ if (!index &&
+ (!cascade(base, &base->tv2, INDEX(0))) &&
+ (!cascade(base, &base->tv3, INDEX(1))) &&
+ !cascade(base, &base->tv4, INDEX(2)))
+ cascade(base, &base->tv5, INDEX(3));
+ ++base->timer_jiffies;
+ list_replace_init(base->tv1.vec + index, head);
+ while (!list_empty(head)) {
+ void (*fn)(unsigned long);
+ unsigned long data;
+ bool irqsafe;
+
+ timer = list_first_entry(head, struct timer_list,entry);
+ fn = timer->function;
+ data = timer->data;
+ irqsafe = tbase_get_irqsafe(timer->base);
+
+ timer_stats_account_timer(timer);
+
+ base->running_timer = timer;
+ detach_expired_timer(timer, base);
+
+ if (irqsafe) {
+ spin_unlock(&base->lock);
+ call_timer_fn(timer, fn, data);
+ spin_lock(&base->lock);
+ } else {
+ spin_unlock_irq(&base->lock);
+ call_timer_fn(timer, fn, data);
+ spin_lock_irq(&base->lock);
+ }
+ }
+ }
+ base->running_timer = NULL;
+ spin_unlock_irq(&base->lock);
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * Find out when the next timer event is due to happen. This
+ * is used on S/390 to stop all activity when a CPU is idle.
+ * This function needs to be called with interrupts disabled.
+ */
+static unsigned long __next_timer_interrupt(struct tvec_base *base)
+{
+ unsigned long timer_jiffies = base->timer_jiffies;
+ unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
+ int index, slot, array, found = 0;
+ struct timer_list *nte;
+ struct tvec *varray[4];
+
+ /* Look for timer events in tv1. */
+ index = slot = timer_jiffies & TVR_MASK;
+ do {
+ list_for_each_entry(nte, base->tv1.vec + slot, entry) {
+ if (tbase_get_deferrable(nte->base))
+ continue;
+
+ found = 1;
+ expires = nte->expires;
+ /* Look at the cascade bucket(s)? */
+ if (!index || slot < index)
+ goto cascade;
+ return expires;
+ }
+ slot = (slot + 1) & TVR_MASK;
+ } while (slot != index);
+
+cascade:
+ /* Calculate the next cascade event */
+ if (index)
+ timer_jiffies += TVR_SIZE - index;
+ timer_jiffies >>= TVR_BITS;
+
+ /* Check tv2-tv5. */
+ varray[0] = &base->tv2;
+ varray[1] = &base->tv3;
+ varray[2] = &base->tv4;
+ varray[3] = &base->tv5;
+
+ for (array = 0; array < 4; array++) {
+ struct tvec *varp = varray[array];
+
+ index = slot = timer_jiffies & TVN_MASK;
+ do {
+ list_for_each_entry(nte, varp->vec + slot, entry) {
+ if (tbase_get_deferrable(nte->base))
+ continue;
+
+ found = 1;
+ if (time_before(nte->expires, expires))
+ expires = nte->expires;
+ }
+ /*
+ * Do we still search for the first timer or are
+ * we looking up the cascade buckets ?
+ */
+ if (found) {
+ /* Look at the cascade bucket(s)? */
+ if (!index || slot < index)
+ break;
+ return expires;
+ }
+ slot = (slot + 1) & TVN_MASK;
+ } while (slot != index);
+
+ if (index)
+ timer_jiffies += TVN_SIZE - index;
+ timer_jiffies >>= TVN_BITS;
+ }
+ return expires;
+}
+
+/*
+ * Check, if the next hrtimer event is before the next timer wheel
+ * event:
+ */
+static unsigned long cmp_next_hrtimer_event(unsigned long now,
+ unsigned long expires)
+{
+ ktime_t hr_delta = hrtimer_get_next_event();
+ struct timespec tsdelta;
+ unsigned long delta;
+
+ if (hr_delta.tv64 == KTIME_MAX)
+ return expires;
+
+ /*
+ * Expired timer available, let it expire in the next tick
+ */
+ if (hr_delta.tv64 <= 0)
+ return now + 1;
+
+ tsdelta = ktime_to_timespec(hr_delta);
+ delta = timespec_to_jiffies(&tsdelta);
+
+ /*
+ * Limit the delta to the max value, which is checked in
+ * tick_nohz_stop_sched_tick():
+ */
+ if (delta > NEXT_TIMER_MAX_DELTA)
+ delta = NEXT_TIMER_MAX_DELTA;
+
+ /*
+ * Take rounding errors in to account and make sure, that it
+ * expires in the next tick. Otherwise we go into an endless
+ * ping pong due to tick_nohz_stop_sched_tick() retriggering
+ * the timer softirq
+ */
+ if (delta < 1)
+ delta = 1;
+ now += delta;
+ if (time_before(now, expires))
+ return now;
+ return expires;
+}
+
+/**
+ * get_next_timer_interrupt - return the jiffy of the next pending timer
+ * @now: current time (in jiffies)
+ */
+unsigned long get_next_timer_interrupt(unsigned long now)
+{
+ struct tvec_base *base = __this_cpu_read(tvec_bases);
+ unsigned long expires = now + NEXT_TIMER_MAX_DELTA;
+
+ /*
+ * Pretend that there is no timer pending if the cpu is offline.
+ * Possible pending timers will be migrated later to an active cpu.
+ */
+ if (cpu_is_offline(smp_processor_id()))
+ return expires;
+
+ spin_lock(&base->lock);
+ if (base->active_timers) {
+ if (time_before_eq(base->next_timer, base->timer_jiffies))
+ base->next_timer = __next_timer_interrupt(base);
+ expires = base->next_timer;
+ }
+ spin_unlock(&base->lock);
+
+ if (time_before_eq(expires, now))
+ return now;
+
+ return cmp_next_hrtimer_event(now, expires);
+}
+#endif
+
+/*
+ * Called from the timer interrupt handler to charge one tick to the current
+ * process. user_tick is 1 if the tick is user time, 0 for system.
+ */
+void update_process_times(int user_tick)
+{
+ struct task_struct *p = current;
+ int cpu = smp_processor_id();
+
+ /* Note: this timer irq context must be accounted for as well. */
+ account_process_tick(p, user_tick);
+ run_local_timers();
+ rcu_check_callbacks(cpu, user_tick);
+#ifdef CONFIG_IRQ_WORK
+ if (in_irq())
+ irq_work_run();
+#endif
+ scheduler_tick();
+ run_posix_cpu_timers(p);
+}
+
+/*
+ * This function runs timers and the timer-tq in bottom half context.
+ */
+static void run_timer_softirq(struct softirq_action *h)
+{
+ struct tvec_base *base = __this_cpu_read(tvec_bases);
+
+ hrtimer_run_pending();
+
+ if (time_after_eq(jiffies, base->timer_jiffies))
+ __run_timers(base);
+}
+
+/*
+ * Called by the local, per-CPU timer interrupt on SMP.
+ */
+void run_local_timers(void)
+{
+ hrtimer_run_queues();
+ raise_softirq(TIMER_SOFTIRQ);
+}
+
+#ifdef __ARCH_WANT_SYS_ALARM
+
+/*
+ * For backwards compatibility? This can be done in libc so Alpha
+ * and all newer ports shouldn't need it.
+ */
+SYSCALL_DEFINE1(alarm, unsigned int, seconds)
+{
+ return alarm_setitimer(seconds);
+}
+
+#endif
+
+static void process_timeout(unsigned long __data)
+{
+ wake_up_process((struct task_struct *)__data);
+}
+
+/**
+ * schedule_timeout - sleep until timeout
+ * @timeout: timeout value in jiffies
+ *
+ * Make the current task sleep until @timeout jiffies have
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
+ * pass before the routine returns. The routine will return 0
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task. In this case the remaining time
+ * in jiffies will be returned, or 0 if the timer expired in time
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
+ * the CPU away without a bound on the timeout. In this case the return
+ * value will be %MAX_SCHEDULE_TIMEOUT.
+ *
+ * In all cases the return value is guaranteed to be non-negative.
+ */
+signed long __sched schedule_timeout(signed long timeout)
+{
+ struct timer_list timer;
+ unsigned long expire;
+
+ switch (timeout)
+ {
+ case MAX_SCHEDULE_TIMEOUT:
+ /*
+ * These two special cases are useful to be comfortable
+ * in the caller. Nothing more. We could take
+ * MAX_SCHEDULE_TIMEOUT from one of the negative value
+ * but I' d like to return a valid offset (>=0) to allow
+ * the caller to do everything it want with the retval.
+ */
+ schedule();
+ goto out;
+ default:
+ /*
+ * Another bit of PARANOID. Note that the retval will be
+ * 0 since no piece of kernel is supposed to do a check
+ * for a negative retval of schedule_timeout() (since it
+ * should never happens anyway). You just have the printk()
+ * that will tell you if something is gone wrong and where.
+ */
+ if (timeout < 0) {
+ printk(KERN_ERR "schedule_timeout: wrong timeout "
+ "value %lx\n", timeout);
+ dump_stack();
+ current->state = TASK_RUNNING;
+ goto out;
+ }
+ }
+
+ expire = timeout + jiffies;
+
+ setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
+ __mod_timer(&timer, expire, false, TIMER_NOT_PINNED);
+ schedule();
+ del_singleshot_timer_sync(&timer);
+
+ /* Remove the timer from the object tracker */
+ destroy_timer_on_stack(&timer);
+
+ timeout = expire - jiffies;
+
+ out:
+ return timeout < 0 ? 0 : timeout;
+}
+EXPORT_SYMBOL(schedule_timeout);
+
+/*
+ * We can use __set_current_state() here because schedule_timeout() calls
+ * schedule() unconditionally.
+ */
+signed long __sched schedule_timeout_interruptible(signed long timeout)
+{
+ __set_current_state(TASK_INTERRUPTIBLE);
+ return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_interruptible);
+
+signed long __sched schedule_timeout_killable(signed long timeout)
+{
+ __set_current_state(TASK_KILLABLE);
+ return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_killable);
+
+signed long __sched schedule_timeout_uninterruptible(signed long timeout)
+{
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_uninterruptible);
+
+static int init_timers_cpu(int cpu)
+{
+ int j;
+ struct tvec_base *base;
+ static char tvec_base_done[NR_CPUS];
+
+ if (!tvec_base_done[cpu]) {
+ static char boot_done;
+
+ if (boot_done) {
+ /*
+ * The APs use this path later in boot
+ */
+ base = kzalloc_node(sizeof(*base), GFP_KERNEL,
+ cpu_to_node(cpu));
+ if (!base)
+ return -ENOMEM;
+
+ /* Make sure tvec_base has TIMER_FLAG_MASK bits free */
+ if (WARN_ON(base != tbase_get_base(base))) {
+ kfree(base);
+ return -ENOMEM;
+ }
+ per_cpu(tvec_bases, cpu) = base;
+ } else {
+ /*
+ * This is for the boot CPU - we use compile-time
+ * static initialisation because per-cpu memory isn't
+ * ready yet and because the memory allocators are not
+ * initialised either.
+ */
+ boot_done = 1;
+ base = &boot_tvec_bases;
+ }
+ spin_lock_init(&base->lock);
+ tvec_base_done[cpu] = 1;
+ } else {
+ base = per_cpu(tvec_bases, cpu);
+ }
+
+
+ for (j = 0; j < TVN_SIZE; j++) {
+ INIT_LIST_HEAD(base->tv5.vec + j);
+ INIT_LIST_HEAD(base->tv4.vec + j);
+ INIT_LIST_HEAD(base->tv3.vec + j);
+ INIT_LIST_HEAD(base->tv2.vec + j);
+ }
+ for (j = 0; j < TVR_SIZE; j++)
+ INIT_LIST_HEAD(base->tv1.vec + j);
+
+ base->timer_jiffies = jiffies;
+ base->next_timer = base->timer_jiffies;
+ base->active_timers = 0;
+ base->all_timers = 0;
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
+{
+ struct timer_list *timer;
+
+ while (!list_empty(head)) {
+ timer = list_first_entry(head, struct timer_list, entry);
+ /* We ignore the accounting on the dying cpu */
+ detach_timer(timer, false);
+ timer_set_base(timer, new_base);
+ internal_add_timer(new_base, timer);
+ }
+}
+
+static void migrate_timers(int cpu)
+{
+ struct tvec_base *old_base;
+ struct tvec_base *new_base;
+ int i;
+
+ BUG_ON(cpu_online(cpu));
+ old_base = per_cpu(tvec_bases, cpu);
+ new_base = get_cpu_var(tvec_bases);
+ /*
+ * 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);
+
+ for (i = 0; i < TVR_SIZE; i++)
+ migrate_timer_list(new_base, old_base->tv1.vec + i);
+ for (i = 0; i < TVN_SIZE; i++) {
+ migrate_timer_list(new_base, old_base->tv2.vec + i);
+ migrate_timer_list(new_base, old_base->tv3.vec + i);
+ migrate_timer_list(new_base, old_base->tv4.vec + i);
+ migrate_timer_list(new_base, old_base->tv5.vec + i);
+ }
+
+ spin_unlock(&old_base->lock);
+ spin_unlock_irq(&new_base->lock);
+ put_cpu_var(tvec_bases);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int timer_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ long cpu = (long)hcpu;
+ int err;
+
+ switch(action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ err = init_timers_cpu(cpu);
+ if (err < 0)
+ return notifier_from_errno(err);
+ break;
+#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ migrate_timers(cpu);
+ break;
+#endif
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block timers_nb = {
+ .notifier_call = timer_cpu_notify,
+};
+
+
+void __init init_timers(void)
+{
+ int err;
+
+ /* ensure there are enough low bits for flags in timer->base pointer */
+ BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
+
+ err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
+ (void *)(long)smp_processor_id());
+ BUG_ON(err != NOTIFY_OK);
+
+ init_timer_stats();
+ register_cpu_notifier(&timers_nb);
+ open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
+}
+
+/**
+ * msleep - sleep safely even with waitqueue interruptions
+ * @msecs: Time in milliseconds to sleep for
+ */
+void msleep(unsigned int msecs)
+{
+ unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+
+ while (timeout)
+ timeout = schedule_timeout_uninterruptible(timeout);
+}
+
+EXPORT_SYMBOL(msleep);
+
+/**
+ * msleep_interruptible - sleep waiting for signals
+ * @msecs: Time in milliseconds to sleep for
+ */
+unsigned long msleep_interruptible(unsigned int msecs)
+{
+ unsigned long timeout = msecs_to_jiffies(msecs) + 1;
+
+ while (timeout && !signal_pending(current))
+ timeout = schedule_timeout_interruptible(timeout);
+ return jiffies_to_msecs(timeout);
+}
+
+EXPORT_SYMBOL(msleep_interruptible);
+
+static int __sched do_usleep_range(unsigned long min, unsigned long max)
+{
+ ktime_t kmin;
+ unsigned long delta;
+
+ kmin = ktime_set(0, min * NSEC_PER_USEC);
+ delta = (max - min) * NSEC_PER_USEC;
+ return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
+}
+
+/**
+ * usleep_range - Drop in replacement for udelay where wakeup is flexible
+ * @min: Minimum time in usecs to sleep
+ * @max: Maximum time in usecs to sleep
+ */
+void usleep_range(unsigned long min, unsigned long max)
+{
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ do_usleep_range(min, max);
+}
+EXPORT_SYMBOL(usleep_range);