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

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

   - various sched/numa updates, for better performance

   - tree wide cleanup of open coded nice levels

   - nohz fix related to rq->nr_running use

   - cpuidle changes and continued consolidation to improve the
     kernel/sched/idle.c high level idle scheduling logic.  As part of
     this effort I pulled cpuidle driver changes from Rafael as well.

   - standardized idle polling amongst architectures

   - continued work on preparing better power/energy aware scheduling

   - sched/rt updates

   - misc fixlets and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sched/numa: Decay ->wakee_flips instead of zeroing
  sched/numa: Update migrate_improves/degrades_locality()
  sched/numa: Allow task switch if load imbalance improves
  sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
  sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
  sched: Initialize rq->age_stamp on processor start
  sched, nohz: Change rq->nr_running to always use wrappers
  sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
  sched: Use clamp() and clamp_val() to make sys_nice() more readable
  sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
  sched/numa: Fix initialization of sched_domain_topology for NUMA
  sched: Call select_idle_sibling() when not affine_sd
  sched: Simplify return logic in sched_read_attr()
  sched: Simplify return logic in sched_copy_attr()
  sched: Fix exec_start/task_hot on migrated tasks
  arm64: Remove TIF_POLLING_NRFLAG
  metag: Remove TIF_POLLING_NRFLAG
  sched/idle: Make cpuidle_idle_call() void
  sched/idle: Reflow cpuidle_idle_call()
  sched/idle: Delay clearing the polling bit
  ...

16 files changed, 67 insertions, 37 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f70a230a2945..6cb1beb47c25 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -548,7 +548,7 @@ static int loop_thread(void *data)
 	struct loop_device *lo = data;
 	struct bio *bio;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3a70ea2f7cd6..56a027d6115e 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -533,7 +533,7 @@ static int nbd_thread(void *data)
 	struct nbd_device *nbd = data;
 	struct request *req;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 	while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
 		/* wait for something to do */
 		wait_event_interruptible(nbd->waiting_wq,
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index a2af73db187b..ef166ad2dbad 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1463,7 +1463,7 @@ static int kcdrwd(void *foobar)
 	struct packet_data *pkt;
 	long min_sleep_time, residue;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 	set_freezable();
 
 	for (;;) {
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 1c4bb4f6ce93..5d665680ae33 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1007,7 +1007,7 @@ static int ipmi_thread(void *data)
 	struct timespec busy_until;
 
 	ipmi_si_set_not_busy(&busy_until);
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 	while (!kthread_should_stop()) {
 		int busy_wait;
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 8236746e46bb..cb7019977c50 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -32,6 +32,7 @@ LIST_HEAD(cpuidle_detected_devices);
 static int enabled_devices;
 static int off __read_mostly;
 static int initialized __read_mostly;
+static bool use_deepest_state __read_mostly;
 
 int cpuidle_disabled(void)
 {
@@ -65,23 +66,42 @@ int cpuidle_play_dead(void)
 }
 
 /**
- * cpuidle_enabled - check if the cpuidle framework is ready
- * @dev: cpuidle device for this cpu
- * @drv: cpuidle driver for this cpu
+ * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode.
+ * @enable: Whether enable or disable the feature.
+ *
+ * If the "deepest idle" mode is enabled, cpuidle will ignore the governor and
+ * always use the state with the greatest exit latency (out of the states that
+ * are not disabled).
  *
- * Return 0 on success, otherwise:
- * -NODEV : the cpuidle framework is not available
- * -EBUSY : the cpuidle framework is not initialized
+ * This function can only be called after cpuidle_pause() to avoid races.
  */
-int cpuidle_enabled(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+void cpuidle_use_deepest_state(bool enable)
 {
-	if (off || !initialized)
-		return -ENODEV;
+	use_deepest_state = enable;
+}
 
-	if (!drv || !dev || !dev->enabled)
-		return -EBUSY;
+/**
+ * cpuidle_find_deepest_state - Find the state of the greatest exit latency.
+ * @drv: cpuidle driver for a given CPU.
+ * @dev: cpuidle device for a given CPU.
+ */
+static int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+				      struct cpuidle_device *dev)
+{
+	unsigned int latency_req = 0;
+	int i, ret = CPUIDLE_DRIVER_STATE_START - 1;
 
-	return 0;
+	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+		struct cpuidle_state_usage *su = &dev->states_usage[i];
+
+		if (s->disabled || su->disable || s->exit_latency <= latency_req)
+			continue;
+
+		latency_req = s->exit_latency;
+		ret = i;
+	}
+	return ret;
 }
 
 /**
@@ -138,6 +158,15 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
  */
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
+	if (off || !initialized)
+		return -ENODEV;
+
+	if (!drv || !dev || !dev->enabled)
+		return -EBUSY;
+
+	if (unlikely(use_deepest_state))
+		return cpuidle_find_deepest_state(drv, dev);
+
 	return cpuidle_curr_governor->select(drv, dev);
 }
 
@@ -169,7 +198,7 @@ int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 void cpuidle_reflect(struct cpuidle_device *dev, int index)
 {
-	if (cpuidle_curr_governor->reflect)
+	if (cpuidle_curr_governor->reflect && !unlikely(use_deepest_state))
 		cpuidle_curr_governor->reflect(dev, index);
 }
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 71b523293354..c4f80c15a48d 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -296,7 +296,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->needs_update = 0;
 	}
 
-	data->last_state_idx = 0;
+	data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
@@ -311,13 +311,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	data->bucket = which_bucket(data->next_timer_us);
 
 	/*
-	 * if the correction factor is 0 (eg first time init or cpu hotplug
-	 * etc), we actually want to start out with a unity factor.
-	 */
-	if (data->correction_factor[data->bucket] == 0)
-		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
-
-	/*
 	 * Force the result of multiplication to be 64 bits even if both
 	 * operands are 32 bits.
 	 * Make sure to round up for half microseconds.
@@ -466,9 +459,17 @@ static int menu_enable_device(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
+	int i;
 
 	memset(data, 0, sizeof(struct menu_device));
 
+	/*
+	 * if the correction factor is 0 (eg first time init or cpu hotplug
+	 * etc), we actually want to start out with a unity factor.
+	 */
+	for(i = 0; i < BUCKETS; i++)
+		data->correction_factor[i] = RESOLUTION * DECAY;
+
 	return 0;
 }
 
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index ab3baa7f9508..8eec1653c9cc 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1803,7 +1803,7 @@ static int ap_poll_thread(void *data)
 	int requests;
 	struct ap_device *ap_dev;
 
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 	while (1) {
 		if (ap_suspend_flag)
 			return 0;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 1d41f4b9114f..f54843023466 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -464,7 +464,7 @@ static int bnx2fc_l2_rcv_thread(void *arg)
 	struct fcoe_percpu_s *bg = arg;
 	struct sk_buff *skb;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 	set_current_state(TASK_INTERRUPTIBLE);
 	while (!kthread_should_stop()) {
 		schedule();
@@ -602,7 +602,7 @@ int bnx2fc_percpu_io_thread(void *arg)
 	struct bnx2fc_work *work, *tmp;
 	LIST_HEAD(work_list);
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 	set_current_state(TASK_INTERRUPTIBLE);
 	while (!kthread_should_stop()) {
 		schedule();
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index b5ffd280a1ae..d6d491c2f004 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -1870,7 +1870,7 @@ int bnx2i_percpu_io_thread(void *arg)
 	struct bnx2i_work *work, *tmp;
 	LIST_HEAD(work_list);
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	while (!kthread_should_stop()) {
 		spin_lock_bh(&p->p_work_lock);
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index d5e105b173f0..00ee0ed642aa 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1872,7 +1872,7 @@ static int fcoe_percpu_receive_thread(void *arg)
 
 	skb_queue_head_init(&tmp);
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 retry:
 	while (!kthread_should_stop()) {
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 23f5ba5e6472..8dd47689d584 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -4515,7 +4515,7 @@ static int ibmvfc_work(void *data)
 	struct ibmvfc_host *vhost = data;
 	int rc;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	while (1) {
 		rc = wait_event_interruptible(vhost->work_wait_q,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index fa764406df68..2ebfb2bb0f42 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2213,7 +2213,7 @@ static int ibmvscsi_work(void *data)
 	struct ibmvscsi_host_data *hostdata = data;
 	int rc;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	while (1) {
 		rc = wait_event_interruptible(hostdata->work_wait_q,
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 59b51c529ba0..294c072e9083 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -731,7 +731,7 @@ lpfc_do_work(void *p)
 	struct lpfc_hba *phba = p;
 	int rc;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 	current->flags |= PF_NOFREEZE;
 	phba->data_flags = 0;
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 19e99cc33724..afc84814e9bb 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4828,7 +4828,7 @@ qla2x00_do_dpc(void *data)
 	ha = (struct qla_hw_data *)data;
 	base_vha = pci_get_drvdata(ha->pdev);
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	while (!kthread_should_stop()) {
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index 989f809f323f..a741da77828a 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -439,12 +439,12 @@ static void binder_set_nice(long nice)
 		set_user_nice(current, nice);
 		return;
 	}
-	min_nice = 20 - current->signal->rlim[RLIMIT_NICE].rlim_cur;
+	min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur);
 	binder_debug(BINDER_DEBUG_PRIORITY_CAP,
 		     "%d: nice value %ld not allowed use %ld instead\n",
 		      current->pid, nice, min_nice);
 	set_user_nice(current, min_nice);
-	if (min_nice < 20)
+	if (min_nice <= MAX_NICE)
 		return;
 	binder_user_error("%d RLIMIT_NICE not set\n", current->pid);
 }
diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c
index b9694b8cb5dd..0ff8c3362a8d 100644
--- a/drivers/staging/lustre/lustre/llite/lloop.c
+++ b/drivers/staging/lustre/lustre/llite/lloop.c
@@ -404,7 +404,7 @@ static int loop_thread(void *data)
 	int refcheck;
 	int ret = 0;
 
-	set_user_nice(current, -20);
+	set_user_nice(current, MIN_NICE);
 
 	lo->lo_state = LLOOP_BOUND;