9 files changed, 100 insertions, 37 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 0669b70fa6a3..9fdba03dc1fc 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -52,8 +52,23 @@ config PREEMPT
 
 endchoice
 
+config PREEMPT_RCU
+        bool "Preemptible RCU"
+        depends on PREEMPT
+        default n
+        help
+          This option reduces the latency of the kernel by making certain
+          RCU sections preemptible. Normally RCU code is non-preemptible, if
+          this option is selected then read-only RCU sections become
+          preemptible. This helps latency, but may expose bugs due to
+          now-naive assumptions about each RCU read-side critical section
+          remaining on a given CPU through its execution.
+
+          Say N if you are unsure.
+
 config RCU_TRACE
         bool "Enable tracing for RCU - currently stats in debugfs"
+        depends on PREEMPT_RCU
         select DEBUG_FS
         default y
         help
diff --git a/kernel/exit.c b/kernel/exit.c
index cd20bf07e9e3..53872bf993fa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1378,7 +1378,7 @@ unlock_sig:
         if (!retval && infop)
                 retval = put_user(0, &infop->si_errno);
         if (!retval && infop)
-                retval = put_user(why, &infop->si_code);
+                retval = put_user((short)why, &infop->si_code);
         if (!retval && infop)
                 retval = put_user(exit_code, &infop->si_status);
         if (!retval && infop)
diff --git a/kernel/module.c b/kernel/module.c
index be4807fb90e4..5d437bffd8dc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2178,10 +2178,20 @@ sys_init_module(void __user *umod,
                 wake_up(&module_wq);
                 return ret;
         }
+        if (ret > 0) {
+                printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
+                                    "it should follow 0/-E convention\n"
+                       KERN_WARNING "%s: loading module anyway...\n",
+                       __func__, mod->name, ret,
+                       __func__);
+                dump_stack();
+        }
 
-        /* Now it's a first class citizen! */
-        mutex_lock(&module_mutex);
+        /* Now it's a first class citizen!  Wake up anyone waiting for it. */
         mod->state = MODULE_STATE_LIVE;
+        wake_up(&module_wq);
+
+        mutex_lock(&module_mutex);
         /* Drop initial reference. */
         module_put(mod);
         unwind_remove_table(mod->unwind_info, 1);
@@ -2190,7 +2200,6 @@ sys_init_module(void __user *umod,
         mod->init_size = 0;
         mod->init_text_size = 0;
         mutex_unlock(&module_mutex);
-        wake_up(&module_wq);
 
         return 0;
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index dcd553cc4ee8..b02e4fc25645 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4422,7 +4422,7 @@ int task_nice(const struct task_struct *p)
 {
         return TASK_NICE(p);
 }
-EXPORT_SYMBOL_GPL(task_nice);
+EXPORT_SYMBOL(task_nice);
 
 /**
  * idle_cpu - is a given cpu idle currently?
@@ -5100,7 +5100,7 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
         time_slice = 0;
         if (p->policy == SCHED_RR) {
                 time_slice = DEF_TIMESLICE;
-        } else {
+        } else if (p->policy != SCHED_FIFO) {
                 struct sched_entity *se = &p->se;
                 unsigned long flags;
                 struct rq *rq;
@@ -5813,6 +5813,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 /* Must be high prio: stop_machine expects to yield to it. */
                 rq = task_rq_lock(p, &flags);
                 __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
+
+                /* Update our root-domain */
+                if (rq->rd) {
+                        BUG_ON(!cpu_isset(cpu, rq->rd->span));
+                        cpu_set(cpu, rq->rd->online);
+                }
+
                 task_rq_unlock(rq, &flags);
                 cpu_rq(cpu)->migration_thread = p;
                 break;
@@ -5821,15 +5828,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
         case CPU_ONLINE_FROZEN:
                 /* Strictly unnecessary, as first user will wake it. */
                 wake_up_process(cpu_rq(cpu)->migration_thread);
-
-                /* Update our root-domain */
-                rq = cpu_rq(cpu);
-                spin_lock_irqsave(&rq->lock, flags);
-                if (rq->rd) {
-                        BUG_ON(!cpu_isset(cpu, rq->rd->span));
-                        cpu_set(cpu, rq->rd->online);
-                }
-                spin_unlock_irqrestore(&rq->lock, flags);
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -6105,8 +6103,6 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
         rq->rd = rd;
 
         cpu_set(rq->cpu, rd->span);
-        if (cpu_isset(rq->cpu, cpu_online_map))
-                cpu_set(rq->cpu, rd->online);
 
         for (class = sched_class_highest; class; class = class->next) {
                 if (class->join_domain)
@@ -7625,6 +7621,11 @@ void sched_move_task(struct task_struct *tsk)
 
         set_task_rq(tsk, task_cpu(tsk));
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+        if (tsk->sched_class->moved_group)
+                tsk->sched_class->moved_group(tsk);
+#endif
+
         if (on_rq) {
                 if (unlikely(running))
                         tsk->sched_class->set_curr_task(rq);
@@ -7721,9 +7722,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
         if (runtime == RUNTIME_INF)
                 return 1ULL << 16;
 
-        runtime *= (1ULL << 16);
-        div64_64(runtime, period);
-        return runtime;
+        return div64_64(runtime << 16, period);
 }
 
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
@@ -7747,25 +7746,40 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
         return total + to_ratio(period, runtime) < global_ratio;
 }
 
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+        struct task_struct *g, *p;
+        do_each_thread(g, p) {
+                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+                        return 1;
+        } while_each_thread(g, p);
+        return 0;
+}
+
 int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 {
         u64 rt_runtime, rt_period;
         int err = 0;
 
-        rt_period = sysctl_sched_rt_period * NSEC_PER_USEC;
+        rt_period = (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
         rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
         if (rt_runtime_us == -1)
-                rt_runtime = rt_period;
+                rt_runtime = RUNTIME_INF;
 
         mutex_lock(&rt_constraints_mutex);
+        read_lock(&tasklist_lock);
+        if (rt_runtime_us == 0 && tg_has_rt_tasks(tg)) {
+                err = -EBUSY;
+                goto unlock;
+        }
         if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
                 err = -EINVAL;
                 goto unlock;
         }
-        if (rt_runtime_us == -1)
-                rt_runtime = RUNTIME_INF;
         tg->rt_runtime = rt_runtime;
  unlock:
+        read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
 
         return err;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3df4d46994ca..e2a530515619 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1353,6 +1353,16 @@ static void set_curr_task_fair(struct rq *rq)
                 set_next_entity(cfs_rq_of(se), se);
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void moved_group_fair(struct task_struct *p)
+{
+        struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+        update_curr(cfs_rq);
+        place_entity(cfs_rq, &p->se, 1);
+}
+#endif
+
 /*
  * All the scheduling class methods:
  */
@@ -1381,6 +1391,10 @@ static const struct sched_class fair_sched_class = {
 
         .prio_changed           = prio_changed_fair,
         .switched_to            = switched_to_fair,
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+        .moved_group            = moved_group_fair,
+#endif
 };
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 76e828517541..0a6d2e516420 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1107,9 +1107,11 @@ static void prio_changed_rt(struct rq *rq, struct task_struct *p,
                         pull_rt_task(rq);
                 /*
                  * If there's a higher priority task waiting to run
-                 * then reschedule.
+                 * then reschedule. Note, the above pull_rt_task
+                 * can release the rq lock and p could migrate.
+                 * Only reschedule if p is still on the same runqueue.
                  */
-                if (p->prio > rq->rt.highest_prio)
+                if (p->prio > rq->rt.highest_prio && rq->curr == p)
                         resched_task(p);
 #else
                 /* For UP simply resched on drop of prio */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c88b5910e7ab..5fd9b9469770 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -42,12 +42,13 @@ long time_esterror = NTP_PHASE_LIMIT;	/* estimated error (us)		*/
 long time_freq;                         /* frequency offset (scaled ppm)*/
 static long time_reftime;               /* time at last adjustment (s)  */
 long time_adjust;
+static long ntp_tick_adj;
 
 static void ntp_update_frequency(void)
 {
         u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
                                 << TICK_LENGTH_SHIFT;
-        second_length += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
+        second_length += (s64)ntp_tick_adj << TICK_LENGTH_SHIFT;
         second_length += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
 
         tick_length_base = second_length;
@@ -342,14 +343,16 @@ int do_adjtimex(struct timex *txc)
                     freq_adj = shift_right(freq_adj, time_constant * 2 +
                                            (SHIFT_PLL + 2) * 2 - SHIFT_NSEC);
                     if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
+                        u64 utemp64;
                         temp64 = time_offset << (SHIFT_NSEC - SHIFT_FLL);
                         if (time_offset < 0) {
-                            temp64 = -temp64;
-                            do_div(temp64, mtemp);
-                            freq_adj -= temp64;
+                            utemp64 = -temp64;
+                            do_div(utemp64, mtemp);
+                            freq_adj -= utemp64;
                         } else {
-                            do_div(temp64, mtemp);
-                            freq_adj += temp64;
+                            utemp64 = temp64;
+                            do_div(utemp64, mtemp);
+                            freq_adj += utemp64;
                         }
                     }
                     freq_adj += time_freq;
@@ -400,3 +403,11 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
         notify_cmos_timer();
         return(result);
 }
+
+static int __init ntp_tick_adj_setup(char *str)
+{
+        ntp_tick_adj = simple_strtol(str, NULL, 0);
+        return 1;
+}
+
+__setup("ntp_tick_adj=", ntp_tick_adj_setup);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2968298f8f36..686da821d376 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -640,7 +640,7 @@ void tick_cancel_sched_timer(int cpu)
 
         if (ts->sched_timer.base)
                 hrtimer_cancel(&ts->sched_timer);
-        ts->tick_stopped = 0;
+
         ts->nohz_mode = NOHZ_MODE_INACTIVE;
 }
 #endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1af9fb050fe2..671af612b768 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -187,8 +187,7 @@ static void change_clocksource(void)
 
         clock->error = 0;
         clock->xtime_nsec = 0;
-        clocksource_calculate_interval(clock,
-                (unsigned long)(current_tick_length()>>TICK_LENGTH_SHIFT));
+        clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
 
         tick_clock_notify();
 
@@ -245,8 +244,7 @@ void __init timekeeping_init(void)
         ntp_clear();
 
         clock = clocksource_get_next();
-        clocksource_calculate_interval(clock,
-                (unsigned long)(current_tick_length()>>TICK_LENGTH_SHIFT));
+        clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
         clock->cycle_last = clocksource_read(clock);
 
         xtime.tv_sec = sec;