8 files changed, 107 insertions, 88 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 72248d1b9e3f..ab81fdd4572b 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2231,19 +2231,25 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  * So only GFP_KERNEL allocations, if all nodes in the cpuset are
  * short of memory, might require taking the callback_mutex mutex.
  *
- * The first loop over the zonelist in mm/page_alloc.c:__alloc_pages()
- * calls here with __GFP_HARDWALL always set in gfp_mask, enforcing
- * hardwall cpusets - no allocation on a node outside the cpuset is
- * allowed (unless in interrupt, of course).
- *
- * The second loop doesn't even call here for GFP_ATOMIC requests
- * (if the __alloc_pages() local variable 'wait' is set).  That check
- * and the checks below have the combined affect in the second loop of
- * the __alloc_pages() routine that:
+ * The first call here from mm/page_alloc:get_page_from_freelist()
+ * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, so
+ * no allocation on a node outside the cpuset is allowed (unless in
+ * interrupt, of course).
+ *
+ * The second pass through get_page_from_freelist() doesn't even call
+ * here for GFP_ATOMIC calls.  For those calls, the __alloc_pages()
+ * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set
+ * in alloc_flags.  That logic and the checks below have the combined
+ * affect that:
  *      in_interrupt - any node ok (current task context irrelevant)
  *      GFP_ATOMIC   - any node ok
  *      GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
  *      GFP_USER     - only nodes in current tasks mems allowed ok.
+ *
+ * Rule:
+ *    Don't call cpuset_zone_allowed() if you can't sleep, unless you
+ *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
+ *    the code that might scan up ancestor cpusets and sleep.
  **/
 
 int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
@@ -2255,6 +2261,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
         if (in_interrupt())
                 return 1;
         node = z->zone_pgdat->node_id;
+        might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
         if (node_isset(node, current->mems_allowed))
                 return 1;
         if (gfp_mask & __GFP_HARDWALL)  /* If hardwall request, stop here */
diff --git a/kernel/exit.c b/kernel/exit.c
index e95b93282210..e06d0c10a24e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -881,14 +881,6 @@ fastcall NORET_TYPE void do_exit(long code)
 
         tsk->flags |= PF_EXITING;
 
-        /*
-         * Make sure we don't try to process any timer firings
-         * while we are already exiting.
-         */
-        tsk->it_virt_expires = cputime_zero;
-        tsk->it_prof_expires = cputime_zero;
-        tsk->it_sched_expires = 0;
-
         if (unlikely(in_atomic()))
                 printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
                                 current->comm, current->pid,
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b7f0388bd71c..01fa2ae98a85 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -456,6 +456,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 
         return ret;
 }
+EXPORT_SYMBOL_GPL(hrtimer_start);
 
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
@@ -484,6 +485,7 @@ int hrtimer_try_to_cancel(struct hrtimer *timer)
         return ret;
 
 }
+EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel);
 
 /**
  * hrtimer_cancel - cancel a timer and wait for the handler to finish.
@@ -504,6 +506,7 @@ int hrtimer_cancel(struct hrtimer *timer)
                 cpu_relax();
         }
 }
+EXPORT_SYMBOL_GPL(hrtimer_cancel);
 
 /**
  * hrtimer_get_remaining - get remaining time for the timer
@@ -522,6 +525,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 
         return rem;
 }
+EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 
 #ifdef CONFIG_NO_IDLE_HZ
 /**
@@ -580,6 +584,7 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
         timer->base = &bases[clock_id];
         timer->node.rb_parent = HRTIMER_INACTIVE;
 }
+EXPORT_SYMBOL_GPL(hrtimer_init);
 
 /**
  * hrtimer_get_res - get the timer resolution for a clock
@@ -599,6 +604,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 
         return 0;
 }
+EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
 /*
  * Expire the per base hrtimer-queue:
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 520f6c59948d..d38d9ec3276c 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -555,9 +555,6 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
         struct cpu_timer_list *next;
         unsigned long i;
 
-        if (CPUCLOCK_PERTHREAD(timer->it_clock) && (p->flags & PF_EXITING))
-                return;
-
         head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
                 p->cpu_timers : p->signal->cpu_timers);
         head += CPUCLOCK_WHICH(timer->it_clock);
@@ -1173,6 +1170,9 @@ static void check_process_timers(struct task_struct *tsk,
                 }
                 t = tsk;
                 do {
+                        if (unlikely(t->flags & PF_EXITING))
+                                continue;
+
                         ticks = cputime_add(cputime_add(t->utime, t->stime),
                                             prof_left);
                         if (!cputime_eq(prof_expires, cputime_zero) &&
@@ -1193,11 +1193,7 @@ static void check_process_timers(struct task_struct *tsk,
                                               t->it_sched_expires > sched)) {
                                 t->it_sched_expires = sched;
                         }
-
-                        do {
-                                t = next_thread(t);
-                        } while (unlikely(t->flags & PF_EXITING));
-                } while (t != tsk);
+                } while ((t = next_thread(t)) != tsk);
         }
 }
 
@@ -1289,30 +1285,30 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 
 #undef  UNEXPIRED
 
-        BUG_ON(tsk->exit_state);
-
         /*
          * Double-check with locks held.
          */
         read_lock(&tasklist_lock);
-        spin_lock(&tsk->sighand->siglock);
+        if (likely(tsk->signal != NULL)) {
+                spin_lock(&tsk->sighand->siglock);
 
-        /*
-         * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
-         * all the timers that are firing, and put them on the firing list.
-         */
-        check_thread_timers(tsk, &firing);
-        check_process_timers(tsk, &firing);
+                /*
+                 * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
+                 * all the timers that are firing, and put them on the firing list.
+                 */
+                check_thread_timers(tsk, &firing);
+                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.
-         */
-        spin_unlock(&tsk->sighand->siglock);
+                /*
+                 * 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.
+                 */
+                spin_unlock(&tsk->sighand->siglock);
+        }
         read_unlock(&tasklist_lock);
 
         /*
diff --git a/kernel/power/main.c b/kernel/power/main.c
index a6d9ef46009e..0a907f0dc56b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -86,6 +86,7 @@ static int suspend_prepare(suspend_state_t state)
                         goto Thaw;
         }
 
+        suspend_console();
         if ((error = device_suspend(PMSG_SUSPEND))) {
                 printk(KERN_ERR "Some devices failed to suspend\n");
                 goto Finish;
@@ -133,6 +134,7 @@ int suspend_enter(suspend_state_t state)
 static void suspend_finish(suspend_state_t state)
 {
         device_resume();
+        resume_console();
         thaw_processes();
         enable_nonboot_cpus();
         if (pm_ops && pm_ops->finish)
diff --git a/kernel/printk.c b/kernel/printk.c
index c056f3324432..19a955619294 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -67,6 +67,7 @@ EXPORT_SYMBOL(oops_in_progress);
  * driver system.
  */
 static DECLARE_MUTEX(console_sem);
+static DECLARE_MUTEX(secondary_console_sem);
 struct console *console_drivers;
 /*
  * This is used for debugging the mess that is the VT code by
@@ -76,7 +77,7 @@ struct console *console_drivers;
  * path in the console code where we end up in places I want
  * locked without the console sempahore held
  */
-static int console_locked;
+static int console_locked, console_suspended;
 
 /*
  * logbuf_lock protects log_buf, log_start, log_end, con_start and logged_chars
@@ -698,6 +699,23 @@ int __init add_preferred_console(char *name, int idx, char *options)
 }
 
 /**
+ * suspend_console - suspend the console subsystem
+ *
+ * This disables printk() while we go into suspend states
+ */
+void suspend_console(void)
+{
+        acquire_console_sem();
+        console_suspended = 1;
+}
+
+void resume_console(void)
+{
+        console_suspended = 0;
+        release_console_sem();
+}
+
+/**
  * acquire_console_sem - lock the console system for exclusive use.
  *
  * Acquires a semaphore which guarantees that the caller has
@@ -708,6 +726,10 @@ int __init add_preferred_console(char *name, int idx, char *options)
 void acquire_console_sem(void)
 {
         BUG_ON(in_interrupt());
+        if (console_suspended) {
+                down(&secondary_console_sem);
+                return;
+        }
         down(&console_sem);
         console_locked = 1;
         console_may_schedule = 1;
@@ -750,6 +772,10 @@ void release_console_sem(void)
         unsigned long _con_start, _log_end;
         unsigned long wake_klogd = 0;
 
+        if (console_suspended) {
+                up(&secondary_console_sem);
+                return;
+        }
         for ( ; ; ) {
                 spin_lock_irqsave(&logbuf_lock, flags);
                 wake_klogd |= log_start - log_end;
diff --git a/kernel/sched.c b/kernel/sched.c
index 4c64f85698ae..c13f1bd2df7d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -665,55 +665,13 @@ static int effective_prio(task_t *p)
 }
 
 /*
- * We place interactive tasks back into the active array, if possible.
- *
- * To guarantee that this does not starve expired tasks we ignore the
- * interactivity of a task if the first expired task had to wait more
- * than a 'reasonable' amount of time. This deadline timeout is
- * load-dependent, as the frequency of array switched decreases with
- * increasing number of running tasks. We also ignore the interactivity
- * if a better static_prio task has expired, and switch periodically
- * regardless, to ensure that highly interactive tasks do not starve
- * the less fortunate for unreasonably long periods.
- */
-static inline int expired_starving(runqueue_t *rq)
-{
-        int limit;
-
-        /*
-         * Arrays were recently switched, all is well
-         */
-        if (!rq->expired_timestamp)
-                return 0;
-
-        limit = STARVATION_LIMIT * rq->nr_running;
-
-        /*
-         * It's time to switch arrays
-         */
-        if (jiffies - rq->expired_timestamp >= limit)
-                return 1;
-
-        /*
-         * There's a better selection in the expired array
-         */
-        if (rq->curr->static_prio > rq->best_expired_prio)
-                return 1;
-
-        /*
-         * All is well
-         */
-        return 0;
-}
-
-/*
  * __activate_task - move a task to the runqueue.
  */
 static void __activate_task(task_t *p, runqueue_t *rq)
 {
         prio_array_t *target = rq->active;
 
-        if (unlikely(batch_task(p) || (expired_starving(rq) && !rt_task(p))))
+        if (batch_task(p))
                 target = rq->expired;
         enqueue_task(p, target);
         rq->nr_running++;
@@ -2532,6 +2490,22 @@ unsigned long long current_sched_time(const task_t *tsk)
 }
 
 /*
+ * We place interactive tasks back into the active array, if possible.
+ *
+ * To guarantee that this does not starve expired tasks we ignore the
+ * interactivity of a task if the first expired task had to wait more
+ * than a 'reasonable' amount of time. This deadline timeout is
+ * load-dependent, as the frequency of array switched decreases with
+ * increasing number of running tasks. We also ignore the interactivity
+ * if a better static_prio task has expired:
+ */
+#define EXPIRED_STARVING(rq) \
+        ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
+                (jiffies - (rq)->expired_timestamp >= \
+                        STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
+                        ((rq)->curr->static_prio > (rq)->best_expired_prio))
+
+/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
@@ -2666,7 +2640,7 @@ void scheduler_tick(void)
 
                 if (!rq->expired_timestamp)
                         rq->expired_timestamp = jiffies;
-                if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
+                if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
                         enqueue_task(p, rq->expired);
                         if (p->static_prio < rq->best_expired_prio)
                                 rq->best_expired_prio = p->static_prio;
diff --git a/kernel/timer.c b/kernel/timer.c
index 67eaf0f54096..9e49deed468c 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -541,6 +541,22 @@ found:
         }
         spin_unlock(&base->lock);
 
+        /*
+         * It can happen that other CPUs service timer IRQs and increment
+         * jiffies, but we have not yet got a local timer tick to process
+         * the timer wheels.  In that case, the expiry time can be before
+         * jiffies, but since the high-resolution timer here is relative to
+         * jiffies, the default expression when high-resolution timers are
+         * not active,
+         *
+         *   time_before(MAX_JIFFY_OFFSET + jiffies, expires)
+         *
+         * would falsely evaluate to true.  If that is the case, just
+         * return jiffies so that we can immediately fire the local timer
+         */
+        if (time_before(expires, jiffies))
+                return jiffies;
+
         if (time_before(hr_expires, expires))
                 return hr_expires;