Merge commit 'v2.6.36' into wip-merge-2.6.36

Conflicts:
	Makefile
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/syscall_table_32.S
	kernel/sched.c
	kernel/time/tick-sched.c

Relevant API and functions changes (solved in this commit):
- (API) .enqueue_task() (enqueue_task_litmus),
  dequeue_task() (dequeue_task_litmus),
  [litmus/sched_litmus.c]
- (API) .select_task_rq() (select_task_rq_litmus)
  [litmus/sched_litmus.c]
- (API) sysrq_dump_trace_buffer() and sysrq_handle_kill_rt_tasks()
  [litmus/sched_trace.c]
- struct kfifo internal buffer name changed (buffer -> buf)
  [litmus/sched_trace.c]
- add_wait_queue_exclusive_locked -> __add_wait_queue_tail_exclusive
  [litmus/fmlp.c]
- syscall numbers for both x86_32 and x86_64

1 files changed, 60 insertions, 42 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index fdf95968e517..cb49883b64e5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -91,8 +91,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 
         do {
                 seq = read_seqbegin(&xtime_lock);
-                xts = current_kernel_time();
-                tom = wall_to_monotonic;
+                xts = __current_kernel_time();
+                tom = __get_wall_to_monotonic();
         } while (read_seqretry(&xtime_lock, seq));
 
         xtim = timespec_to_ktime(xts);
@@ -146,12 +146,8 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 static int hrtimer_get_target(int this_cpu, int pinned)
 {
 #ifdef CONFIG_NO_HZ
-        if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
-                int preferred_cpu = get_nohz_load_balancer();
-
-                if (preferred_cpu >= 0)
-                        return preferred_cpu;
-        }
+        if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
+                return get_nohz_timer_target();
 #endif
         return this_cpu;
 }
@@ -614,7 +610,7 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 static void retrigger_next_event(void *arg)
 {
         struct hrtimer_cpu_base *base;
-        struct timespec realtime_offset;
+        struct timespec realtime_offset, wtm;
         unsigned long seq;
 
         if (!hrtimer_hres_active())
@@ -622,10 +618,9 @@ static void retrigger_next_event(void *arg)
 
         do {
                 seq = read_seqbegin(&xtime_lock);
-                set_normalized_timespec(&realtime_offset,
-                                        -wall_to_monotonic.tv_sec,
-                                        -wall_to_monotonic.tv_nsec);
+                wtm = __get_wall_to_monotonic();
         } while (read_seqretry(&xtime_lock, seq));
+        set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
 
         base = &__get_cpu_var(hrtimer_bases);
 
@@ -938,6 +933,7 @@ static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 {
         if (hrtimer_is_queued(timer)) {
+                unsigned long state;
                 int reprogram;
 
                 /*
@@ -951,8 +947,13 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
                 debug_deactivate(timer);
                 timer_stats_hrtimer_clear_start_info(timer);
                 reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
-                __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
-                                 reprogram);
+                /*
+                 * 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;
@@ -1190,11 +1191,10 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel);
  */
 ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 {
-        struct hrtimer_clock_base *base;
         unsigned long flags;
         ktime_t rem;
 
-        base = lock_hrtimer_base(timer, &flags);
+        lock_hrtimer_base(timer, &flags);
         rem = hrtimer_expires_remaining(timer);
         unlock_hrtimer_base(timer, &flags);
 
@@ -1331,6 +1331,9 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
                 BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
                 enqueue_hrtimer(timer, base);
         }
+
+        WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
+
         timer->state &= ~HRTIMER_STATE_CALLBACK;
 }
 
@@ -1844,35 +1847,15 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout_range - sleep until timeout
+ * 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
- *
- * 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
+ * @clock:      timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
  */
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
-                               const enum hrtimer_mode mode)
+int __sched
+schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+                               const enum hrtimer_mode mode, int clock)
 {
         struct hrtimer_sleeper t;
 
@@ -1894,7 +1877,7 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
                 return -EINTR;
         }
 
-        hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+        hrtimer_init_on_stack(&t.timer, clock, mode);
         hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
         hrtimer_init_sleeper(&t, current);
@@ -1913,6 +1896,41 @@ int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 
         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);
 
 /**