Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Optimized support for Intel "Cluster-on-Die" (CoD) topologies (Dave
     Hansen)

   - Various sched/idle refinements for better idle handling (Nicolas
     Pitre, Daniel Lezcano, Chuansheng Liu, Vincent Guittot)

   - sched/numa updates and optimizations (Rik van Riel)

   - sysbench speedup (Vincent Guittot)

   - capacity calculation cleanups/refactoring (Vincent Guittot)

   - Various cleanups to thread group iteration (Oleg Nesterov)

   - Double-rq-lock removal optimization and various refactorings
     (Kirill Tkhai)

   - various sched/deadline fixes

  ... and lots of other changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/dl: Use dl_bw_of() under rcu_read_lock_sched()
  sched/fair: Delete resched_cpu() from idle_balance()
  sched, time: Fix build error with 64 bit cputime_t on 32 bit systems
  sched: Improve sysbench performance by fixing spurious active migration
  sched/x86: Fix up typo in topology detection
  x86, sched: Add new topology for multi-NUMA-node CPUs
  sched/rt: Use resched_curr() in task_tick_rt()
  sched: Use rq->rd in sched_setaffinity() under RCU read lock
  sched: cleanup: Rename 'out_unlock' to 'out_free_new_mask'
  sched: Use dl_bw_of() under RCU read lock
  sched/fair: Remove duplicate code from can_migrate_task()
  sched, mips, ia64: Remove __ARCH_WANT_UNLOCKED_CTXSW
  sched: print_rq(): Don't use tasklist_lock
  sched: normalize_rt_tasks(): Don't use _irqsave for tasklist_lock, use task_rq_lock()
  sched: Fix the task-group check in tg_has_rt_tasks()
  sched/fair: Leverage the idle state info when choosing the "idlest" cpu
  sched: Let the scheduler see CPU idle states
  sched/deadline: Fix inter- exclusive cpusets migrations
  sched/deadline: Clear dl_entity params when setscheduling to different class
  sched/numa: Kill the wrong/dead TASK_DEAD check in task_numa_fault()
  ...

11 files changed, 8 insertions, 20 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ee9df5e3f5eb..125150dc6e81 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -223,8 +223,14 @@ void cpuidle_uninstall_idle_handler(void)
 {
 	if (enabled_devices) {
 		initialized = 0;
-		kick_all_cpus_sync();
+		wake_up_all_idle_cpus();
 	}
+
+	/*
+	 * Make sure external observers (such as the scheduler)
+	 * are done looking at pointed idle states.
+	 */
+	synchronize_rcu();
 }
 
 /**
@@ -530,11 +536,6 @@ EXPORT_SYMBOL_GPL(cpuidle_register);
 
 #ifdef CONFIG_SMP
 
-static void smp_callback(void *v)
-{
-	/* we already woke the CPU up, nothing more to do */
-}
-
 /*
  * This function gets called when a part of the kernel has a new latency
  * requirement.  This means we need to get all processors out of their C-state,
@@ -544,7 +545,7 @@ static void smp_callback(void *v)
 static int cpuidle_latency_notify(struct notifier_block *b,
 		unsigned long l, void *v)
 {
-	smp_call_function(smp_callback, NULL, 1);
+	wake_up_all_idle_cpus();
 	return NOTIFY_OK;
 }
 
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 77711623b973..7bcbf863656e 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -400,7 +400,6 @@ int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible)
 		}
 		schedule();
 		remove_wait_queue(&vga_wait_queue, &wait);
-		set_current_state(TASK_RUNNING);
 	}
 	return rc;
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index ab472c557d18..0505559f0965 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -720,7 +720,6 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c)
 
 	io_schedule();
 
-	set_task_state(current, TASK_RUNNING);
 	remove_wait_queue(&c->free_buffer_wait, &wait);
 
 	dm_bufio_lock(c);
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index 90cca5e3805f..ef31b77404ef 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -121,7 +121,6 @@ static int kpowerswd(void *param)
 		unsigned long soft_power_reg = (unsigned long) param;
 
 		schedule_timeout_interruptible(pwrsw_enabled ? HZ : HZ/POWERSWITCH_POLL_PER_SEC);
-		__set_current_state(TASK_RUNNING);
 
 		if (unlikely(!pwrsw_enabled))
 			continue;
diff --git a/drivers/s390/net/claw.c b/drivers/s390/net/claw.c
index fbc6701bef30..213e54ee8a66 100644
--- a/drivers/s390/net/claw.c
+++ b/drivers/s390/net/claw.c
@@ -481,7 +481,6 @@ claw_open(struct net_device *dev)
                 spin_unlock_irqrestore(
 			get_ccwdev_lock(privptr->channel[i].cdev), saveflags);
                 schedule();
-		set_current_state(TASK_RUNNING);
                 remove_wait_queue(&privptr->channel[i].wait, &wait);
                 if(rc != 0)
                         ccw_check_return_code(privptr->channel[i].cdev, rc);
@@ -828,7 +827,6 @@ claw_release(struct net_device *dev)
 	        spin_unlock_irqrestore(
 			get_ccwdev_lock(privptr->channel[i].cdev), saveflags);
 	        schedule();
-		set_current_state(TASK_RUNNING);
 	        remove_wait_queue(&privptr->channel[i].wait, &wait);
 	        if (rc != 0) {
                         ccw_check_return_code(privptr->channel[i].cdev, rc);
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 00ee0ed642aa..4a8ac7d8c76b 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1884,7 +1884,6 @@ retry:
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_bh(&p->fcoe_rx_list.lock);
 			schedule();
-			set_current_state(TASK_RUNNING);
 			goto retry;
 		}
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index dabd25429c58..db3dbd999cb6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4875,7 +4875,6 @@ qla2x00_do_dpc(void *data)
 		    "DPC handler sleeping.\n");
 
 		schedule();
-		__set_current_state(TASK_RUNNING);
 
 		if (!base_vha->flags.init_done || ha->flags.mbox_busy)
 			goto end_loop;
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 86f1a91e896f..14c9c8d18d02 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -3215,7 +3215,6 @@ kiblnd_connd (void *arg)
 
 		schedule_timeout(timeout);
 
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&kiblnd_data.kib_connd_waitq, &wait);
 		spin_lock_irqsave(&kiblnd_data.kib_connd_lock, flags);
 	}
@@ -3432,7 +3431,6 @@ kiblnd_scheduler(void *arg)
 		busy_loops = 0;
 
 		remove_wait_queue(&sched->ibs_waitq, &wait);
-		set_current_state(TASK_RUNNING);
 		spin_lock_irqsave(&sched->ibs_lock, flags);
 	}
 
@@ -3507,7 +3505,6 @@ kiblnd_failover_thread(void *arg)
 
 		rc = schedule_timeout(long_sleep ? cfs_time_seconds(10) :
 						   cfs_time_seconds(1));
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&kiblnd_data.kib_failover_waitq, &wait);
 		write_lock_irqsave(glock, flags);
 
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
index bcfee7c21942..d29f5f134b89 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
@@ -2232,7 +2232,6 @@ ksocknal_connd (void *arg)
 		nloops = 0;
 		schedule_timeout(timeout);
 
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&ksocknal_data.ksnd_connd_waitq, &wait);
 		spin_lock_bh(connd_lock);
 	}
diff --git a/drivers/staging/lustre/lustre/libcfs/fail.c b/drivers/staging/lustre/lustre/libcfs/fail.c
index 1bf9c90b4789..e73ca3df9734 100644
--- a/drivers/staging/lustre/lustre/libcfs/fail.c
+++ b/drivers/staging/lustre/lustre/libcfs/fail.c
@@ -131,7 +131,6 @@ int __cfs_fail_timeout_set(__u32 id, __u32 value, int ms, int set)
 		       id, ms);
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(cfs_time_seconds(ms) / 1000);
-		set_current_state(TASK_RUNNING);
 		CERROR("cfs_fail_timeout id %x awake\n", id);
 	}
 	return ret;
diff --git a/drivers/tty/bfin_jtag_comm.c b/drivers/tty/bfin_jtag_comm.c
index 8096fcbe2dc1..d7b198c400c7 100644
--- a/drivers/tty/bfin_jtag_comm.c
+++ b/drivers/tty/bfin_jtag_comm.c
@@ -77,7 +77,6 @@ bfin_jc_emudat_manager(void *arg)
 			pr_debug("waiting for readers\n");
 			__set_current_state(TASK_UNINTERRUPTIBLE);
 			schedule();
-			__set_current_state(TASK_RUNNING);
 			continue;
 		}