Merge branch 'v28-range-hrtimers-for-linus-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'v28-range-hrtimers-for-linus-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (37 commits)
  hrtimers: add missing docbook comments to struct hrtimer
  hrtimers: simplify hrtimer_peek_ahead_timers()
  hrtimers: fix docbook comments
  DECLARE_PER_CPU needs linux/percpu.h
  hrtimers: fix typo
  rangetimers: fix the bug reported by Ingo for real
  rangetimer: fix BUG_ON reported by Ingo
  rangetimer: fix x86 build failure for the !HRTIMERS case
  select: fix alpha OSF wrapper
  select: fix alpha OSF wrapper
  hrtimer: peek at the timer queue just before going idle
  hrtimer: make the futex() system call use the per process slack value
  hrtimer: make the nanosleep() syscall use the per process slack
  hrtimer: fix signed/unsigned bug in slack estimator
  hrtimer: show the timer ranges in /proc/timer_list
  hrtimer: incorporate feedback from Peter Zijlstra
  hrtimer: add a hrtimer_start_range() function
  hrtimer: another build fix
  hrtimer: fix build bug found by Ingo
  hrtimer: make select() and poll() use the hrtimer range feature
  ...

7 files changed, 132 insertions, 7 deletions

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 9a4e35cd5f79..2b3645b1acf4 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -20,6 +20,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/percpu.h>
+
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -101,9 +103,14 @@ enum hrtimer_cb_mode {
 /**
  * struct hrtimer - the basic hrtimer structure
  * @node:       red black tree node for time ordered insertion
- * @expires:    the absolute expiry time in the hrtimers internal
+ * @_expires:   the absolute expiry time in the hrtimers internal
  *              representation. The time is related to the clock on
- *              which the timer is based.
+ *              which the timer is based. Is setup by adding
+ *              slack to the _softexpires value. For non range timers
+ *              identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *              The time which was given as expiry time when the timer
+ *              was armed.
  * @function:   timer expiry callback function
  * @base:       pointer to the timer base (per cpu and per clock)
  * @state:      state information (See bit values above)
@@ -121,7 +128,8 @@ enum hrtimer_cb_mode {
  */
 struct hrtimer {
         struct rb_node                  node;
-        ktime_t                         expires;
+        ktime_t                         _expires;
+        ktime_t                         _softexpires;
         enum hrtimer_restart            (*function)(struct hrtimer *);
         struct hrtimer_clock_base       *base;
         unsigned long                   state;
@@ -201,6 +209,71 @@ struct hrtimer_cpu_base {
 #endif
 };
 
+static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
+{
+        timer->_expires = time;
+        timer->_softexpires = time;
+}
+
+static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta)
+{
+        timer->_softexpires = time;
+        timer->_expires = ktime_add_safe(time, delta);
+}
+
+static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
+{
+        timer->_softexpires = time;
+        timer->_expires = ktime_add_safe(time, ns_to_ktime(delta));
+}
+
+static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
+{
+        timer->_expires.tv64 = tv64;
+        timer->_softexpires.tv64 = tv64;
+}
+
+static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
+{
+        timer->_expires = ktime_add_safe(timer->_expires, time);
+        timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
+}
+
+static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
+{
+        timer->_expires = ktime_add_ns(timer->_expires, ns);
+        timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
+}
+
+static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
+{
+        return timer->_expires;
+}
+
+static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
+{
+        return timer->_softexpires;
+}
+
+static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
+{
+        return timer->_expires.tv64;
+}
+static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
+{
+        return timer->_softexpires.tv64;
+}
+
+static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
+{
+        return ktime_to_ns(timer->_expires);
+}
+
+static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
+{
+    return ktime_sub(timer->_expires, timer->base->get_time());
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 struct clock_event_device;
 
@@ -221,6 +294,8 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
         return timer->base->cpu_base->hres_active;
 }
 
+extern void hrtimer_peek_ahead_timers(void);
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -243,6 +318,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
  * is expired in the next softirq when the clock was advanced.
  */
 static inline void clock_was_set(void) { }
+static inline void hrtimer_peek_ahead_timers(void) { }
 
 static inline void hres_timers_resume(void) { }
 
@@ -264,6 +340,10 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
 
+
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+
+
 /* Exported timer functions: */
 
 /* Initialize timers: */
@@ -288,12 +368,25 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 /* Basic timer operations: */
 extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
                          const enum hrtimer_mode mode);
+extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+                        unsigned long range_ns, const enum hrtimer_mode mode);
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
+static inline int hrtimer_start_expires(struct hrtimer *timer,
+                                                enum hrtimer_mode mode)
+{
+        unsigned long delta;
+        ktime_t soft, hard;
+        soft = hrtimer_get_softexpires(timer);
+        hard = hrtimer_get_expires(timer);
+        delta = ktime_to_ns(ktime_sub(hard, soft));
+        return hrtimer_start_range_ns(timer, soft, delta, mode);
+}
+
 static inline int hrtimer_restart(struct hrtimer *timer)
 {
-        return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+        return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
@@ -350,6 +443,10 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
 extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
                                  struct task_struct *tsk);
 
+extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+                                                const enum hrtimer_mode mode);
+extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
+
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
 extern void hrtimer_run_pending(void);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 021d8e720c79..23fd8909b9e5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -170,6 +170,7 @@ extern struct group_info init_groups;
         .cpu_timers     = INIT_CPU_TIMERS(tsk.cpu_timers),              \
         .fs_excl        = ATOMIC_INIT(0),                               \
         .pi_lock        = __SPIN_LOCK_UNLOCKED(tsk.pi_lock),            \
+        .timer_slack_ns = 50000, /* 50 usec default slack */            \
         .pids = {                                                       \
                 [PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),            \
                 [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),           \
diff --git a/include/linux/poll.h b/include/linux/poll.h
index ef453828877a..badd98ab06f6 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -114,11 +114,13 @@ void zero_fd_set(unsigned long nr, unsigned long *fdset)
 
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
 
-extern int do_select(int n, fd_set_bits *fds, s64 *timeout);
+extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time);
 extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
-                       s64 *timeout);
+                       struct timespec *end_time);
 extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
-                           fd_set __user *exp, s64 *timeout);
+                           fd_set __user *exp, struct timespec *end_time);
+
+extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
 
 #endif /* KERNEL */
 
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 5ad79198d6f9..48d887e3c6e7 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -78,4 +78,11 @@
 #define PR_GET_SECUREBITS 27
 #define PR_SET_SECUREBITS 28
 
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 10bff55b0824..5ca620573d47 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1345,6 +1345,12 @@ struct task_struct {
         int latency_record_count;
         struct latency_record latency_record[LT_SAVECOUNT];
 #endif
+        /*
+         * time slack values; these are used to round up poll() and
+         * select() etc timeout values. These are in nanoseconds.
+         */
+        unsigned long timer_slack_ns;
+        unsigned long default_timer_slack_ns;
 };
 
 /*
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 38a56477f27a..e6b820f8b56b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -38,6 +38,14 @@ struct restart_block {
 #endif
                         u64 expires;
                 } nanosleep;
+                /* For poll */
+                struct {
+                        struct pollfd __user *ufds;
+                        int nfds;
+                        int has_timeout;
+                        unsigned long tv_sec;
+                        unsigned long tv_nsec;
+                } poll;
         };
 };
 
diff --git a/include/linux/time.h b/include/linux/time.h
index 4f1c9db57707..ce321ac5c8f8 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -40,6 +40,8 @@ extern struct timezone sys_tz;
 #define NSEC_PER_SEC    1000000000L
 #define FSEC_PER_SEC    1000000000000000L
 
+#define TIME_T_MAX      (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1)
+
 static inline int timespec_equal(const struct timespec *a,
                                  const struct timespec *b)
 {
@@ -74,6 +76,8 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon,
                             const unsigned int min, const unsigned int sec);
 
 extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
+extern struct timespec timespec_add_safe(const struct timespec lhs,
+                                         const struct timespec rhs);
 
 /*
  * sub = lhs - rhs, in normalized form