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 are:

   - lockless wakeup support for futexes and IPC message queues
     (Davidlohr Bueso, Peter Zijlstra)

   - Replace spinlocks with atomics in thread_group_cputimer(), to
     improve scalability (Jason Low)

   - NUMA balancing improvements (Rik van Riel)

   - SCHED_DEADLINE improvements (Wanpeng Li)

   - clean up and reorganize preemption helpers (Frederic Weisbecker)

   - decouple page fault disabling machinery from the preemption
     counter, to improve debuggability and robustness (David
     Hildenbrand)

   - SCHED_DEADLINE documentation updates (Luca Abeni)

   - topology CPU masks cleanups (Bartosz Golaszewski)

   - /proc/sched_debug improvements (Srikar Dronamraju)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits)
  sched/deadline: Remove needless parameter in dl_runtime_exceeded()
  sched: Remove superfluous resetting of the p->dl_throttled flag
  sched/deadline: Drop duplicate init_sched_dl_class() declaration
  sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target
  sched/deadline: Make init_sched_dl_class() __init
  sched/deadline: Optimize pull_dl_task()
  sched/preempt: Add static_key() to preempt_notifiers
  sched/preempt: Fix preempt notifiers documentation about hlist_del() within unsafe iteration
  sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
  sched/debug: Add sum_sleep_runtime to /proc/<pid>/sched
  sched/debug: Replace vruntime with wait_sum in /proc/sched_debug
  sched/debug: Properly format runnable tasks in /proc/sched_debug
  sched/numa: Only consider less busy nodes as numa balancing destinations
  Revert 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced")
  sched/fair: Prevent throttling in early pick_next_task_fair()
  preempt: Reorganize the notrace definitions a bit
  preempt: Use preempt_schedule_context() as the official tracing preemption point
  sched: Make preempt_schedule_context() function-tracing safe
  x86: Remove cpu_sibling_mask() and cpu_core_mask()
  x86: Replace cpu_**_mask() with topology_**_cpumask()
  ...

16 files changed, 298 insertions, 204 deletions

diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index b59b5a52637e..e56272c919b5 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -8,8 +8,7 @@
 #ifndef CONFIG_SMP
 /*
  * The following implementation only for uniprocessor machines.
- * For UP, it's relies on the fact that pagefault_disable() also disables
- * preemption to ensure mutual exclusion.
+ * It relies on preempt_disable() ensuring mutual exclusion.
  *
  */
 
@@ -38,6 +37,7 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
+	preempt_disable();
 	pagefault_disable();
 
 	ret = -EFAULT;
@@ -72,6 +72,7 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 out_pagefault_enable:
 	pagefault_enable();
+	preempt_enable();
 
 	if (ret == 0) {
 		switch (cmp) {
@@ -106,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	u32 val;
 
+	preempt_disable();
 	if (unlikely(get_user(val, uaddr) != 0))
 		return -EFAULT;
 
@@ -113,6 +115,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	*uval = val;
+	preempt_enable();
 
 	return 0;
 }
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index eb6f9e6c3075..d0a7a4753db2 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -79,11 +79,8 @@ static __always_inline bool should_resched(void)
 #ifdef CONFIG_PREEMPT
 extern asmlinkage void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
-
-#ifdef CONFIG_CONTEXT_TRACKING
-extern asmlinkage void preempt_schedule_context(void);
-#define __preempt_schedule_context() preempt_schedule_context()
-#endif
+extern asmlinkage void preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace() preempt_schedule_notrace()
 #endif /* CONFIG_PREEMPT */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 86c12c93e3cf..8fdcb783197d 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -2,7 +2,6 @@
 #define _LINUX_BH_H
 
 #include <linux/preempt.h>
-#include <linux/preempt_mask.h>
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f4af03404b97..dfd59d6bc6f0 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -1,7 +1,7 @@
 #ifndef LINUX_HARDIRQ_H
 #define LINUX_HARDIRQ_H
 
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <linux/vtime.h>
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 9286a46b7d69..6aefcd0031a6 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -65,6 +65,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
+	preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -73,6 +74,7 @@ static inline void *kmap_atomic(struct page *page)
 static inline void __kunmap_atomic(void *addr)
 {
 	pagefault_enable();
+	preempt_enable();
 }
 
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 696d22312b31..bb9b075f0eb0 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -50,9 +50,8 @@ extern struct fs_struct init_fs;
 	.cpu_timers	= INIT_CPU_TIMERS(sig.cpu_timers),		\
 	.rlim		= INIT_RLIMITS,					\
 	.cputimer	= { 						\
-		.cputime = INIT_CPUTIME,				\
-		.running = 0,						\
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock),	\
+		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
+		.running	= 0,					\
 	},								\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 657fab4efab3..c27dde7215b5 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -141,6 +141,7 @@ static inline void __iomem *
 io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset)
 {
+	preempt_disable();
 	pagefault_disable();
 	return ((char __force __iomem *) mapping) + offset;
 }
@@ -149,6 +150,7 @@ static inline void
 io_mapping_unmap_atomic(void __iomem *vaddr)
 {
 	pagefault_enable();
+	preempt_enable();
 }
 
 /* Non-atomic map/unmap */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3a5b48e52a9e..060dd7b61c6d 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -244,7 +244,8 @@ static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
 
 #if defined(CONFIG_MMU) && \
 	(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
-void might_fault(void);
+#define might_fault() __might_fault(__FILE__, __LINE__)
+void __might_fault(const char *file, int line);
 #else
 static inline void might_fault(void) { }
 #endif
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 0081f000e34b..c92ebd100d9b 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -52,10 +52,15 @@ struct lglock {
 	static struct lglock name = { .lock = &name ## _lock }
 
 void lg_lock_init(struct lglock *lg, char *name);
+
 void lg_local_lock(struct lglock *lg);
 void lg_local_unlock(struct lglock *lg);
 void lg_local_lock_cpu(struct lglock *lg, int cpu);
 void lg_local_unlock_cpu(struct lglock *lg, int cpu);
+
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2);
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2);
+
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index de83b4eb1642..0f1534acaf60 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -10,13 +10,117 @@
 #include <linux/list.h>
 
 /*
- * We use the MSB mostly because its available; see <linux/preempt_mask.h> for
- * the other bits -- can't include that header due to inclusion hell.
+ * We put the hardirq and softirq counter into the preemption
+ * counter. The bitmask has the following meaning:
+ *
+ * - bits 0-7 are the preemption count (max preemption depth: 256)
+ * - bits 8-15 are the softirq count (max # of softirqs: 256)
+ *
+ * The hardirq count could in theory be the same as the number of
+ * interrupts in the system, but we run all interrupt handlers with
+ * interrupts disabled, so we cannot have nesting interrupts. Though
+ * there are a few palaeontologic drivers which reenable interrupts in
+ * the handler, so we need more than one bit here.
+ *
+ *         PREEMPT_MASK:	0x000000ff
+ *         SOFTIRQ_MASK:	0x0000ff00
+ *         HARDIRQ_MASK:	0x000f0000
+ *             NMI_MASK:	0x00100000
+ *       PREEMPT_ACTIVE:	0x00200000
+ * PREEMPT_NEED_RESCHED:	0x80000000
  */
+#define PREEMPT_BITS	8
+#define SOFTIRQ_BITS	8
+#define HARDIRQ_BITS	4
+#define NMI_BITS	1
+
+#define PREEMPT_SHIFT	0
+#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
+#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
+
+#define __IRQ_MASK(x)	((1UL << (x))-1)
+
+#define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
+#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
+#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
+
+#define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
+#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
+#define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET	(1UL << NMI_SHIFT)
+
+#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
+
+#define PREEMPT_ACTIVE_BITS	1
+#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+
+/* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
+/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
 #include <asm/preempt.h>
 
+#define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
+#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
+#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+				 | NMI_MASK))
+
+/*
+ * Are we doing bottom half or hardware interrupt processing?
+ * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
+ */
+#define in_irq()		(hardirq_count())
+#define in_softirq()		(softirq_count())
+#define in_interrupt()		(irq_count())
+#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
+
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi()	(preempt_count() & NMI_MASK)
+
+#if defined(CONFIG_PREEMPT_COUNT)
+# define PREEMPT_DISABLE_OFFSET 1
+#else
+# define PREEMPT_DISABLE_OFFSET 0
+#endif
+
+/*
+ * The preempt_count offset needed for things like:
+ *
+ *  spin_lock_bh()
+ *
+ * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
+ * softirqs, such that unlock sequences of:
+ *
+ *  spin_unlock();
+ *  local_bh_enable();
+ *
+ * Work as expected.
+ */
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+
+/*
+ * Are we running in atomic context?  WARNING: this macro cannot
+ * always detect atomic context; in particular, it cannot know about
+ * held spinlocks in non-preemptible kernels.  Thus it should not be
+ * used in the general case to determine whether sleeping is possible.
+ * Do not use in_atomic() in driver code.
+ */
+#define in_atomic()	(preempt_count() != 0)
+
+/*
+ * Check whether we were atomic before we did preempt_disable():
+ * (used by the scheduler)
+ */
+#define in_atomic_preempt_off() \
+		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
@@ -33,6 +137,18 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#define preempt_active_enter() \
+do { \
+	preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+	barrier(); \
+} while (0)
+
+#define preempt_active_exit() \
+do { \
+	barrier(); \
+	preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
+} while (0)
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -49,6 +165,8 @@ do { \
 
 #define preempt_enable_no_resched() sched_preempt_enable_no_resched()
 
+#define preemptible()	(preempt_count() == 0 && !irqs_disabled())
+
 #ifdef CONFIG_PREEMPT
 #define preempt_enable() \
 do { \
@@ -57,52 +175,46 @@ do { \
 		__preempt_schedule(); \
 } while (0)
 
+#define preempt_enable_notrace() \
+do { \
+	barrier(); \
+	if (unlikely(__preempt_count_dec_and_test())) \
+		__preempt_schedule_notrace(); \
+} while (0)
+
 #define preempt_check_resched() \
 do { \
 	if (should_resched()) \
 		__preempt_schedule(); \
 } while (0)
 
-#else
+#else /* !CONFIG_PREEMPT */
 #define preempt_enable() \
 do { \
 	barrier(); \
 	preempt_count_dec(); \
 } while (0)
-#define preempt_check_resched() do { } while (0)
-#endif
-
-#define preempt_disable_notrace() \
-do { \
-	__preempt_count_inc(); \
-	barrier(); \
-} while (0)
 
-#define preempt_enable_no_resched_notrace() \
+#define preempt_enable_notrace() \
 do { \
 	barrier(); \
 	__preempt_count_dec(); \
 } while (0)
 
-#ifdef CONFIG_PREEMPT
-
-#ifndef CONFIG_CONTEXT_TRACKING
-#define __preempt_schedule_context() __preempt_schedule()
-#endif
+#define preempt_check_resched() do { } while (0)
+#endif /* CONFIG_PREEMPT */
 
-#define preempt_enable_notrace() \
+#define preempt_disable_notrace() \
 do { \
+	__preempt_count_inc(); \
 	barrier(); \
-	if (unlikely(__preempt_count_dec_and_test())) \
-		__preempt_schedule_context(); \
 } while (0)
-#else
-#define preempt_enable_notrace() \
+
+#define preempt_enable_no_resched_notrace() \
 do { \
 	barrier(); \
 	__preempt_count_dec(); \
 } while (0)
-#endif
 
 #else /* !CONFIG_PREEMPT_COUNT */
 
@@ -121,6 +233,7 @@ do { \
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
 #define preempt_enable_notrace()		barrier()
+#define preemptible()				0
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
deleted file mode 100644
index dbeec4d4a3be..000000000000
--- a/include/linux/preempt_mask.h
+++ /dev/null
@@ -1,117 +0,0 @@
-#ifndef LINUX_PREEMPT_MASK_H
-#define LINUX_PREEMPT_MASK_H
-
-#include <linux/preempt.h>
-
-/*
- * We put the hardirq and softirq counter into the preemption
- * counter. The bitmask has the following meaning:
- *
- * - bits 0-7 are the preemption count (max preemption depth: 256)
- * - bits 8-15 are the softirq count (max # of softirqs: 256)
- *
- * The hardirq count could in theory be the same as the number of
- * interrupts in the system, but we run all interrupt handlers with
- * interrupts disabled, so we cannot have nesting interrupts. Though
- * there are a few palaeontologic drivers which reenable interrupts in
- * the handler, so we need more than one bit here.
- *
- * PREEMPT_MASK:	0x000000ff
- * SOFTIRQ_MASK:	0x0000ff00
- * HARDIRQ_MASK:	0x000f0000
- *     NMI_MASK:	0x00100000
- * PREEMPT_ACTIVE:	0x00200000
- */
-#define PREEMPT_BITS	8
-#define SOFTIRQ_BITS	8
-#define HARDIRQ_BITS	4
-#define NMI_BITS	1
-
-#define PREEMPT_SHIFT	0
-#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
-#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
-#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
-
-#define __IRQ_MASK(x)	((1UL << (x))-1)
-
-#define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
-#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
-#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
-#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
-
-#define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
-#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
-#define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
-#define NMI_OFFSET	(1UL << NMI_SHIFT)
-
-#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
-
-#define PREEMPT_ACTIVE_BITS	1
-#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
-#define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
-#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
-				 | NMI_MASK))
-
-/*
- * Are we doing bottom half or hardware interrupt processing?
- * Are we in a softirq context? Interrupt context?
- * in_softirq - Are we currently processing softirq or have bh disabled?
- * in_serving_softirq - Are we currently processing softirq?
- */
-#define in_irq()		(hardirq_count())
-#define in_softirq()		(softirq_count())
-#define in_interrupt()		(irq_count())
-#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
-
-/*
- * Are we in NMI context?
- */
-#define in_nmi()	(preempt_count() & NMI_MASK)
-
-#if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_CHECK_OFFSET 1
-#else
-# define PREEMPT_CHECK_OFFSET 0
-#endif
-
-/*
- * The preempt_count offset needed for things like:
- *
- *  spin_lock_bh()
- *
- * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
- * softirqs, such that unlock sequences of:
- *
- *  spin_unlock();
- *  local_bh_enable();
- *
- * Work as expected.
- */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
-
-/*
- * Are we running in atomic context?  WARNING: this macro cannot
- * always detect atomic context; in particular, it cannot know about
- * held spinlocks in non-preemptible kernels.  Thus it should not be
- * used in the general case to determine whether sleeping is possible.
- * Do not use in_atomic() in driver code.
- */
-#define in_atomic()	((preempt_count() & ~PREEMPT_ACTIVE) != 0)
-
-/*
- * Check whether we were atomic before we did preempt_disable():
- * (used by the scheduler, *after* releasing the kernel lock)
- */
-#define in_atomic_preempt_off() \
-		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_CHECK_OFFSET)
-
-#ifdef CONFIG_PREEMPT_COUNT
-# define preemptible()	(preempt_count() == 0 && !irqs_disabled())
-#else
-# define preemptible()	0
-#endif
-
-#endif /* LINUX_PREEMPT_MASK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 659f5729cacc..d4193d5613cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -25,7 +25,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -174,7 +174,12 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 extern void calc_global_load(unsigned long ticks);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -214,9 +219,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
 #define TASK_PARKED		512
-#define TASK_STATE_MAX		1024
+#define TASK_NOLOAD		1024
+#define TASK_STATE_MAX		2048
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -226,6 +232,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
 
+#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
 #define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
@@ -241,7 +249,8 @@ extern char ___assert_task_state[1 - 2*!!(
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0)
+				 (task->flags & PF_FROZEN) == 0 && \
+				 (task->state & TASK_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
@@ -568,6 +577,23 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+
 #ifdef CONFIG_PREEMPT_COUNT
 #define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
 #else
@@ -585,18 +611,16 @@ struct task_cputime {
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
- * @cputime:		thread group interval timers.
+ * @cputime_atomic:	atomic thread group interval timers.
  * @running:		non-zero when there are timers running and
  * 			@cputime receives updates.
- * @lock:		lock for fields in this struct.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
-	struct task_cputime cputime;
+	struct task_cputime_atomic cputime_atomic;
 	int running;
-	raw_spinlock_t lock;
 };
 
 #include <linux/rwsem.h>
@@ -901,6 +925,50 @@ enum cpu_idle_type {
 #define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function, where the fact that the queue is
+ * not used again will be easy to see by inspection.
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+struct wake_q_node {
+	struct wake_q_node *next;
+};
+
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define WAKE_Q(name)					\
+	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+extern void wake_q_add(struct wake_q_head *head,
+		       struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
+/*
  * sched-domains (multiprocessor balancing) declarations:
  */
 #ifdef CONFIG_SMP
@@ -1335,8 +1403,6 @@ struct task_struct {
 	int rcu_read_lock_nesting;
 	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
@@ -1367,7 +1433,7 @@ struct task_struct {
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
+	unsigned long jobctl;	/* JOBCTL_*, siglock protected */
 
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
@@ -1513,6 +1579,8 @@ struct task_struct {
 	/* Protection of the PI data structures: */
 	raw_spinlock_t pi_lock;
 
+	struct wake_q_node wake_q;
+
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
 	struct rb_root pi_waiters;
@@ -1726,6 +1794,7 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+	int pagefault_disabled;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2079,22 +2148,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 
-#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task,
-				    unsigned int mask);
+				    unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
-				      unsigned int mask);
+				      unsigned long mask);
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
@@ -2964,11 +3033,6 @@ static __always_inline bool need_resched(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
-	raw_spin_lock_init(&sig->cputimer.lock);
-}
-
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
@@ -3082,13 +3146,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 static inline unsigned long task_rlimit(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
 }
 
 static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
 }
 
 static inline unsigned long rlimit(unsigned int limit)
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 909b6e43b694..73ddad1e0fa3 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -191,8 +191,8 @@ static inline int cpu_to_mem(int cpu)
 #ifndef topology_core_id
 #define topology_core_id(cpu)			((void)(cpu), 0)
 #endif
-#ifndef topology_thread_cpumask
-#define topology_thread_cpumask(cpu)		cpumask_of(cpu)
+#ifndef topology_sibling_cpumask
+#define topology_sibling_cpumask(cpu)		cpumask_of(cpu)
 #endif
 #ifndef topology_core_cpumask
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
@@ -201,7 +201,7 @@ static inline int cpu_to_mem(int cpu)
 #ifdef CONFIG_SCHED_SMT
 static inline const struct cpumask *cpu_smt_mask(int cpu)
 {
-	return topology_thread_cpumask(cpu);
+	return topology_sibling_cpumask(cpu);
 }
 #endif
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ecd3319dac33..ae572c138607 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -1,21 +1,30 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
-#include <linux/preempt.h>
+#include <linux/sched.h>
 #include <asm/uaccess.h>
 
+static __always_inline void pagefault_disabled_inc(void)
+{
+	current->pagefault_disabled++;
+}
+
+static __always_inline void pagefault_disabled_dec(void)
+{
+	current->pagefault_disabled--;
+	WARN_ON(current->pagefault_disabled < 0);
+}
+
 /*
- * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
+ * These routines enable/disable the pagefault handler. If disabled, it will
+ * not take any locks and go straight to the fixup table.
  *
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
+ * User access methods will not sleep when called from a pagefault_disabled()
+ * environment.
  */
 static inline void pagefault_disable(void)
 {
-	preempt_count_inc();
+	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.
@@ -25,18 +34,31 @@ static inline void pagefault_disable(void)
 
 static inline void pagefault_enable(void)
 {
-#ifndef CONFIG_PREEMPT
 	/*
 	 * make sure to issue those last loads/stores before enabling
 	 * the pagefault handler again.
 	 */
 	barrier();
-	preempt_count_dec();
-#else
-	preempt_enable();
-#endif
+	pagefault_disabled_dec();
 }
 
+/*
+ * Is the pagefault handler disabled? If so, user access methods will not sleep.
+ */
+#define pagefault_disabled() (current->pagefault_disabled != 0)
+
+/*
+ * The pagefault handler is in general disabled by pagefault_disable() or
+ * when in irq context (via in_atomic()).
+ *
+ * This function should only be used by the fault handlers. Other users should
+ * stick to pagefault_disabled().
+ * Please NEVER use preempt_disable() to disable the fault handler. With
+ * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled.
+ * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT.
+ */
+#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2db83349865b..d69ac4ecc88b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -969,7 +969,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *);
  * on that signal.
  */
 static inline int
-wait_on_bit(void *word, int bit, unsigned mode)
+wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -994,7 +994,7 @@ wait_on_bit(void *word, int bit, unsigned mode)
  * on that signal.
  */
 static inline int
-wait_on_bit_io(void *word, int bit, unsigned mode)
+wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1020,7 +1020,8 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
  * received a signal and the mode permitted wakeup on that signal.
  */
 static inline int
-wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
+wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
+		    unsigned long timeout)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1047,7 +1048,8 @@ wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
  * on that signal.
  */
 static inline int
-wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
+		   unsigned mode)
 {
 	might_sleep();
 	if (!test_bit(bit, word))
@@ -1075,7 +1077,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock(void *word, int bit, unsigned mode)
+wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
@@ -1099,7 +1101,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode)
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock_io(void *word, int bit, unsigned mode)
+wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
@@ -1125,7 +1127,8 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode)
  * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
+wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
+			unsigned mode)
 {
 	might_sleep();
 	if (!test_and_set_bit(bit, word))
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 30fedaf3e56a..d57a575fe31f 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -147,7 +147,8 @@ TRACE_EVENT(sched_switch,
 		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
+				{ 128, "K" }, { 256, "W" }, { 512, "P" },
+				{ 1024, "N" }) : "R",
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );