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
  ...

48 files changed, 759 insertions, 662 deletions

diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 3d6ce6d56fc..48bbea6898b 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -73,12 +73,14 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TIF_SYSCALL_AUDIT	4	/* syscall audit active */
 #define TIF_DIE_IF_KERNEL	9	/* dik recursion lock */
 #define TIF_MEMDIE		13	/* is terminating due to OOM killer */
+#define TIF_POLLING_NRFLAG	14	/* idle is polling for TIF_NEED_RESCHED */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
+#define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 
 /* Work to do on interrupt/exception return.  */
 #define _TIF_WORK_MASK		(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
@@ -92,8 +94,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TS_UAC_NOFIX		0x0002	/* ! flags as they match          */
 #define TS_UAC_SIGBUS		0x0004	/* ! userspace part of 'osf_sysinfo' */
 #define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
-#define TS_POLLING		0x0010	/* idle task polling need_resched,
-					   skip sending interrupt */
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK	1
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 0bc94b1fd1a..71e1fec6d31 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -185,6 +185,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return &cpu_topology[cpu].core_sibling;
 }
 
+/*
+ * The current assumption is that we can power gate each core independently.
+ * This will be superseded by DT binding once available.
+ */
+const struct cpumask *cpu_corepower_mask(int cpu)
+{
+	return &cpu_topology[cpu].thread_sibling;
+}
+
 static void update_siblings_masks(unsigned int cpuid)
 {
 	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
@@ -266,6 +275,20 @@ void store_cpu_topology(unsigned int cpuid)
 		cpu_topology[cpuid].socket_id, mpidr);
 }
 
+static inline const int cpu_corepower_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
+}
+
+static struct sched_domain_topology_level arm_topology[] = {
+#ifdef CONFIG_SCHED_MC
+	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
@@ -289,4 +312,7 @@ void __init init_cpu_topology(void)
 	smp_wmb();
 
 	parse_dt_topology();
+
+	/* Set scheduler topology descriptor */
+	set_sched_topology(arm_topology);
 }
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 720e70b66ff..7b8e3a2a00f 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -95,13 +95,11 @@ static inline struct thread_info *current_thread_info(void)
  *  TIF_NEED_RESCHED	- rescheduling necessary
  *  TIF_NOTIFY_RESUME	- callback before returning to user
  *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
- *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
  */
 #define TIF_SIGPENDING		0
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_SYSCALL_TRACE	8
-#define TIF_POLLING_NRFLAG	16
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
 #define TIF_RESTORE_SIGMASK	20
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 5957cf61f89..5b17418b422 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -107,6 +107,7 @@ struct thread_info {
 #define TIF_MCA_INIT		18	/* this task is processing MCA or INIT */
 #define TIF_DB_DISABLED		19	/* debug trap disabled for fsyscall */
 #define TIF_RESTORE_RSE		21	/* user RBS is newer than kernel RBS */
+#define TIF_POLLING_NRFLAG	22	/* idle is polling for TIF_NEED_RESCHED */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
@@ -118,6 +119,7 @@ struct thread_info {
 #define _TIF_MCA_INIT		(1 << TIF_MCA_INIT)
 #define _TIF_DB_DISABLED	(1 << TIF_DB_DISABLED)
 #define _TIF_RESTORE_RSE	(1 << TIF_RESTORE_RSE)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 
 /* "work to do on user-return" bits */
 #define TIF_ALLWORK_MASK	(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SYSCALL_AUDIT|\
@@ -125,7 +127,6 @@ struct thread_info {
 /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */
 #define TIF_WORK_MASK		(TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT))
 
-#define TS_POLLING		1 	/* true if in idle loop and not sleeping */
 #define TS_RESTORE_SIGMASK	2	/* restore signal mask in do_signal() */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 5cb55a1e606..3202aa74e0d 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -46,30 +46,6 @@
 
 void build_cpu_to_node_map(void);
 
-#define SD_CPU_INIT (struct sched_domain) {		\
-	.parent			= NULL,			\
-	.child			= NULL,			\
-	.groups			= NULL,			\
-	.min_interval		= 1,			\
-	.max_interval		= 4,			\
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 2,			\
-	.busy_idx		= 2,			\
-	.idle_idx		= 1,			\
-	.newidle_idx		= 0,			\
-	.wake_idx		= 0,			\
-	.forkexec_idx		= 0,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_WAKE_AFFINE,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-	.nr_balance_failed	= 0,			\
-}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index b19e9c588a1..47711336119 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -117,10 +117,8 @@ static inline int kstack_end(void *addr)
 #define TIF_SECCOMP		5	/* secure computing */
 #define TIF_RESTORE_SIGMASK	6	/* restore signal mask in do_signal() */
 #define TIF_NOTIFY_RESUME	7	/* callback before returning to user */
-#define TIF_POLLING_NRFLAG      8	/* true if poll_idle() is polling
-					   TIF_NEED_RESCHED */
-#define TIF_MEMDIE		9	/* is terminating due to OOM killer */
-#define TIF_SYSCALL_TRACEPOINT  10	/* syscall tracepoint instrumentation */
+#define TIF_MEMDIE		8	/* is terminating due to OOM killer */
+#define TIF_SYSCALL_TRACEPOINT	9	/* syscall tracepoint instrumentation */
 
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e2a4232c587..10ffffef041 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -766,6 +766,28 @@ int setup_profiling_timer(unsigned int multiplier)
 	return 0;
 }
 
+#ifdef CONFIG_SCHED_SMT
+/* cpumask of CPUs with asymetric SMT dependancy */
+static const int powerpc_smt_flags(void)
+{
+	int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		flags |= SD_ASYM_PACKING;
+	}
+	return flags;
+}
+#endif
+
+static struct sched_domain_topology_level powerpc_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	cpumask_var_t old_mask;
@@ -790,15 +812,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 	dump_numa_cpu_topology();
 
-}
+	set_sched_topology(powerpc_topology);
 
-int arch_sd_sibling_asym_packing(void)
-{
-	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
-		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
-		return SD_ASYM_PACKING;
-	}
-	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 05425b18c0a..56af53093d2 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -26,21 +26,12 @@ extern struct cpu_topology_s390 cpu_topology[NR_CPUS];
 
 #define mc_capable() 1
 
-static inline const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	return &cpu_topology[cpu].core_mask;
-}
-
-static inline const struct cpumask *cpu_book_mask(int cpu)
-{
-	return &cpu_topology[cpu].book_mask;
-}
-
 int topology_cpu_init(struct cpu *);
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
 void store_topology(struct sysinfo_15_1_x *info);
 void topology_expect_change(void);
+const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #else /* CONFIG_SCHED_BOOK */
 
@@ -64,8 +55,6 @@ static inline void s390_init_cpu_topology(void)
 };
 #endif
 
-#define SD_BOOK_INIT	SD_CPU_INIT
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index fa3b8cdaada..355a16c5570 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -445,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu)
 	return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
 }
 
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_mask;
+}
+
+static const struct cpumask *cpu_book_mask(int cpu)
+{
+	return &cpu_topology[cpu].book_mask;
+}
+
+static struct sched_domain_topology_level s390_topology[] = {
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 static int __init topology_init(void)
 {
 	if (!MACHINE_HAS_TOPOLOGY) {
@@ -453,6 +470,9 @@ static int __init topology_init(void)
 	}
 	set_topology_timer();
 out:
+
+	set_sched_topology(s390_topology);
+
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 729aa107f64..d767ff9f59b 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -129,6 +129,7 @@ extern void _cpu_idle(void);
 #define TIF_MEMDIE		7	/* OOM killer at work */
 #define TIF_NOTIFY_RESUME	8	/* callback before returning to user */
 #define TIF_SYSCALL_TRACEPOINT	9	/* syscall tracepoint instrumentation */
+#define TIF_POLLING_NRFLAG	10	/* idle is polling for TIF_NEED_RESCHED */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -140,6 +141,7 @@ extern void _cpu_idle(void);
 #define _TIF_MEMDIE		(1<<TIF_MEMDIE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+#define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 
 /* Work to do on any return to user space. */
 #define _TIF_ALLWORK_MASK \
@@ -162,7 +164,6 @@ extern void _cpu_idle(void);
 #ifdef __tilegx__
 #define TS_COMPAT		0x0001	/* 32-bit compatibility mode */
 #endif
-#define TS_POLLING		0x0004	/* in idle loop but not sleeping */
 #define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index d15c0d8d550..93831184423 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -44,39 +44,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
 /* For now, use numa node -1 for global allocation. */
 #define pcibus_to_node(bus)		((void)(bus), -1)
 
-/*
- * TILE architecture has many cores integrated in one processor, so we need
- * setup bigger balance_interval for both CPU/NODE scheduling domains to
- * reduce process scheduling costs.
- */
-
-/* sched_domains SD_CPU_INIT for TILE architecture */
-#define SD_CPU_INIT (struct sched_domain) {				\
-	.min_interval		= 4,					\
-	.max_interval		= 128,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 2,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 0*SD_WAKE_AFFINE			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 32,					\
-}
-
 /* By definition, we create nodes based on online memory. */
 #define node_has_online_mem(nid) 1
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 47e5de25ba7..854053889d4 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -83,6 +83,7 @@ struct thread_info {
 #define TIF_FORK		18	/* ret_from_fork */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
+#define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
 #define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
@@ -106,6 +107,7 @@ struct thread_info {
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
@@ -191,8 +193,6 @@ static inline struct thread_info *current_thread_info(void)
  * have to worry about atomic accesses.
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-#define TS_POLLING		0x0004	/* idle task polling need_resched,
-					   skip sending interrupt */
 #define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 3ab03430211..f3a1f04ed4c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -844,21 +844,10 @@ static int apm_do_idle(void)
 	int polling;
 	int err = 0;
 
-	polling = !!(current_thread_info()->status & TS_POLLING);
-	if (polling) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we
-		 * test NEED_RESCHED:
-		 */
-		smp_mb();
-	}
 	if (!need_resched()) {
 		idled = 1;
 		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err);
 	}
-	if (polling)
-		current_thread_info()->status |= TS_POLLING;
 
 	if (!idled)
 		return 0;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f70a230a294..6cb1beb47c2 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 3a70ea2f7cd..56a027d6115 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 a2af73db187..ef166ad2dba 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 1c4bb4f6ce9..5d665680ae3 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 8236746e46b..cb7019977c5 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 71b52329335..c4f80c15a48 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 ab3baa7f950..8eec1653c9c 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)