Merge tag 'sched-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core facilities:

   - Add the "Lazy preemption" model (CONFIG_PREEMPT_LAZY=y), which
     optimizes fair-class preemption by delaying preemption requests to
     the tick boundary, while working as full preemption for
     RR/FIFO/DEADLINE classes. (Peter Zijlstra)
        - x86: Enable Lazy preemption (Peter Zijlstra)
        - riscv: Enable Lazy preemption (Jisheng Zhang)

   - Initialize idle tasks only once (Thomas Gleixner)

   - sched/ext: Remove sched_fork() hack (Thomas Gleixner)

  Fair scheduler:

   - Optimize the PLACE_LAG when se->vlag is zero (Huang Shijie)

  Idle loop:

   - Optimize the generic idle loop by removing unnecessary memory
     barrier (Zhongqiu Han)

  RSEQ:

   - Improve cache locality of RSEQ concurrency IDs for intermittent
     workloads (Mathieu Desnoyers)

  Waitqueues:

   - Make wake_up_{bit,var} less fragile (Neil Brown)

  PSI:

   - Pass enqueue/dequeue flags to psi callbacks directly (Johannes
     Weiner)

  Preparatory patches for proxy execution:

   - Add move_queued_task_locked helper (Connor O'Brien)

   - Consolidate pick_*_task to task_is_pushable helper (Connor O'Brien)

   - Split out __schedule() deactivate task logic into a helper (John
     Stultz)

   - Split scheduler and execution contexts (Peter Zijlstra)

   - Make mutex::wait_lock irq safe (Juri Lelli)

   - Expose __mutex_owner() (Juri Lelli)

   - Remove wakeups from under mutex::wait_lock (Peter Zijlstra)

  Misc fixes and cleanups:

   - Remove unused __HAVE_THREAD_FUNCTIONS hook support (David
     Disseldorp)

   - Update the comment for TIF_NEED_RESCHED_LAZY (Sebastian Andrzej
     Siewior)

   - Remove unused bit_wait_io_timeout (Dr. David Alan Gilbert)

   - remove the DOUBLE_TICK feature (Huang Shijie)

   - fix the comment for PREEMPT_SHORT (Huang Shijie)

   - Fix unnused variable warning (Christian Loehle)

   - No PREEMPT_RT=y for all{yes,mod}config"

* tag 'sched-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  sched, x86: Update the comment for TIF_NEED_RESCHED_LAZY.
  sched: No PREEMPT_RT=y for all{yes,mod}config
  riscv: add PREEMPT_LAZY support
  sched, x86: Enable Lazy preemption
  sched: Enable PREEMPT_DYNAMIC for PREEMPT_RT
  sched: Add Lazy preemption model
  sched: Add TIF_NEED_RESCHED_LAZY infrastructure
  sched/ext: Remove sched_fork() hack
  sched: Initialize idle tasks only once
  sched: psi: pass enqueue/dequeue flags to psi callbacks directly
  sched/uclamp: Fix unnused variable warning
  sched: Split scheduler and execution contexts
  sched: Split out __schedule() deactivate task logic into a helper
  sched: Consolidate pick_*_task to task_is_pushable helper
  sched: Add move_queued_task_locked helper
  locking/mutex: Expose __mutex_owner()
  locking/mutex: Make mutex::wait_lock irq safe
  locking/mutex: Remove wakeups from under mutex::wait_lock
  sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads
  sched: idle: Optimize the generic idle loop by removing needless memory barrier
  ...

9 files changed, 458 insertions, 103 deletions

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 1e50cdb83ae5..fc61d0205c97 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -64,7 +64,8 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
+	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
+	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |			\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 6813171afccb..16149f6625e4 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -17,8 +17,9 @@
 #endif
 
 #define XFER_TO_GUEST_MODE_WORK						\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
-	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
+	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \
+	 _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME |			\
+	 ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bc..381d22eba088 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -782,6 +782,7 @@ struct vm_area_struct {
 struct mm_cid {
 	u64 time;
 	int cid;
+	int recent_cid;
 };
 #endif
 
@@ -852,6 +853,27 @@ struct mm_struct {
 		 * When the next mm_cid scan is due (in jiffies).
 		 */
 		unsigned long mm_cid_next_scan;
+		/**
+		 * @nr_cpus_allowed: Number of CPUs allowed for mm.
+		 *
+		 * Number of CPUs allowed in the union of all mm's
+		 * threads allowed CPUs.
+		 */
+		unsigned int nr_cpus_allowed;
+		/**
+		 * @max_nr_cid: Maximum number of concurrency IDs allocated.
+		 *
+		 * Track the highest number of concurrency IDs allocated for the
+		 * mm.
+		 */
+		atomic_t max_nr_cid;
+		/**
+		 * @cpus_allowed_lock: Lock protecting mm cpus_allowed.
+		 *
+		 * Provide mutual exclusion for mm cpus_allowed and
+		 * mm nr_cpus_allowed updates.
+		 */
+		raw_spinlock_t cpus_allowed_lock;
 #endif
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* size of all page tables */
@@ -1170,18 +1192,30 @@ static inline int mm_cid_clear_lazy_put(int cid)
 	return cid & ~MM_CID_LAZY_PUT;
 }
 
+/*
+ * mm_cpus_allowed: Union of all mm's threads allowed CPUs.
+ */
+static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm)
+{
+	unsigned long bitmap = (unsigned long)mm;
+
+	bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	/* Skip cpu_bitmap */
+	bitmap += cpumask_size();
+	return (struct cpumask *)bitmap;
+}
+
 /* Accessor for struct mm_struct's cidmask. */
 static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
 {
-	unsigned long cid_bitmap = (unsigned long)mm;
+	unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm);
 
-	cid_bitmap += offsetof(struct mm_struct, cpu_bitmap);
-	/* Skip cpu_bitmap */
+	/* Skip mm_cpus_allowed */
 	cid_bitmap += cpumask_size();
 	return (struct cpumask *)cid_bitmap;
 }
 
-static inline void mm_init_cid(struct mm_struct *mm)
+static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 {
 	int i;
 
@@ -1189,17 +1223,22 @@ static inline void mm_init_cid(struct mm_struct *mm)
 		struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i);
 
 		pcpu_cid->cid = MM_CID_UNSET;
+		pcpu_cid->recent_cid = MM_CID_UNSET;
 		pcpu_cid->time = 0;
 	}
+	mm->nr_cpus_allowed = p->nr_cpus_allowed;
+	atomic_set(&mm->max_nr_cid, 0);
+	raw_spin_lock_init(&mm->cpus_allowed_lock);
+	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	cpumask_clear(mm_cidmask(mm));
 }
 
-static inline int mm_alloc_cid_noprof(struct mm_struct *mm)
+static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p)
 {
 	mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid);
 	if (!mm->pcpu_cid)
 		return -ENOMEM;
-	mm_init_cid(mm);
+	mm_init_cid(mm, p);
 	return 0;
 }
 #define mm_alloc_cid(...)	alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
@@ -1212,16 +1251,31 @@ static inline void mm_destroy_cid(struct mm_struct *mm)
 
 static inline unsigned int mm_cid_size(void)
 {
-	return cpumask_size();
+	return 2 * cpumask_size();	/* mm_cpus_allowed(), mm_cidmask(). */
+}
+
+static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask)
+{
+	struct cpumask *mm_allowed = mm_cpus_allowed(mm);
+
+	if (!mm)
+		return;
+	/* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */
+	raw_spin_lock(&mm->cpus_allowed_lock);
+	cpumask_or(mm_allowed, mm_allowed, cpumask);
+	WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed));
+	raw_spin_unlock(&mm->cpus_allowed_lock);
 }
 #else /* CONFIG_SCHED_MM_CID */
-static inline void mm_init_cid(struct mm_struct *mm) { }
-static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { }
+static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; }
 static inline void mm_destroy_cid(struct mm_struct *mm) { }
+
 static inline unsigned int mm_cid_size(void)
 {
 	return 0;
 }
+static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { }
 #endif /* CONFIG_SCHED_MM_CID */
 
 struct mmu_gather;
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index ce76f1a45722..ca86235ac15c 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -486,6 +486,7 @@ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
 extern bool preempt_model_none(void);
 extern bool preempt_model_voluntary(void);
 extern bool preempt_model_full(void);
+extern bool preempt_model_lazy(void);
 
 #else
 
@@ -502,6 +503,11 @@ static inline bool preempt_model_full(void)
 	return IS_ENABLED(CONFIG_PREEMPT);
 }
 
+static inline bool preempt_model_lazy(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_LAZY);
+}
+
 #endif
 
 static inline bool preempt_model_rt(void)
@@ -519,7 +525,7 @@ static inline bool preempt_model_rt(void)
  */
 static inline bool preempt_model_preemptible(void)
 {
-	return preempt_model_full() || preempt_model_rt();
+	return preempt_model_full() || preempt_model_lazy() || preempt_model_rt();
 }
 
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb343136ddd0..1d5cc3e50884 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1898,7 +1898,7 @@ extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 # define task_thread_info(task)	(&(task)->thread_info)
-#elif !defined(__HAVE_THREAD_FUNCTIONS)
+#else
 # define task_thread_info(task)	((struct thread_info *)(task)->stack)
 #endif
 
@@ -2002,7 +2002,8 @@ static inline void set_tsk_need_resched(struct task_struct *tsk)
 
 static inline void clear_tsk_need_resched(struct task_struct *tsk)
 {
-	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
+	atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY,
+			   (atomic_long_t *)&task_thread_info(tsk)->flags);
 }
 
 static inline int test_tsk_need_resched(struct task_struct *tsk)
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 1ddbde64a31b..2799e7284fff 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -199,7 +199,6 @@ struct sched_ext_entity {
 #ifdef CONFIG_EXT_GROUP_SCHED
 	struct cgroup		*cgrp_moving_from;
 #endif
-	/* must be the last field, see init_scx_entity() */
 	struct list_head	tasks_node;
 };
 
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 6c2fef89a4fd..cffad65bdc6a 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -34,7 +34,7 @@ static __always_inline unsigned long *end_of_stack(const struct task_struct *tas
 #endif
 }
 
-#elif !defined(__HAVE_THREAD_FUNCTIONS)
+#else
 
 #define task_stack_page(task)	((void *)(task)->stack)
 
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 9ea0b28068f4..cf2446c9c30d 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -59,6 +59,14 @@ enum syscall_work_bit {
 
 #include <asm/thread_info.h>
 
+#ifndef TIF_NEED_RESCHED_LAZY
+#ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY
+#error Inconsistent PREEMPT_LAZY
+#endif
+#define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED
+#define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED
+#endif
+
 #ifdef __KERNEL__
 
 #ifndef arch_set_restart_data
@@ -179,22 +187,27 @@ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti
 
 #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H
 
-static __always_inline bool tif_need_resched(void)
+static __always_inline bool tif_test_bit(int bit)
 {
-	return arch_test_bit(TIF_NEED_RESCHED,
+	return arch_test_bit(bit,
 			     (unsigned long *)(&current_thread_info()->flags));
 }
 
 #else
 
-static __always_inline bool tif_need_resched(void)
+static __always_inline bool tif_test_bit(int bit)
 {
-	return test_bit(TIF_NEED_RESCHED,
+	return test_bit(bit,
 			(unsigned long *)(&current_thread_info()->flags));
 }
 
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
 
+static __always_inline bool tif_need_resched(void)
+{
+	return tif_test_bit(TIF_NEED_RESCHED);
+}
+
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
 static inline int arch_within_stack_frames(const void * const stack,
 					   const void * const stackend,
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 7725b7579b78..9e29d79fc790 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -8,7 +8,7 @@
 #include <linux/wait.h>
 
 struct wait_bit_key {
-	void			*flags;
+	unsigned long		*flags;
 	int			bit_nr;
 	unsigned long		timeout;
 };
@@ -23,14 +23,14 @@ struct wait_bit_queue_entry {
 
 typedef int wait_bit_action_f(struct wait_bit_key *key, int mode);
 
-void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit);
+void __wake_up_bit(struct wait_queue_head *wq_head, unsigned long *word, int bit);
 int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
 int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
-void wake_up_bit(void *word, int bit);
-int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode);
-int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout);
-int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode);
-struct wait_queue_head *bit_waitqueue(void *word, int bit);
+void wake_up_bit(unsigned long *word, int bit);
+int out_of_line_wait_on_bit(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode);
+int out_of_line_wait_on_bit_timeout(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout);
+int out_of_line_wait_on_bit_lock(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode);
+struct wait_queue_head *bit_waitqueue(unsigned long *word, int bit);
 extern void __init wait_bit_init(void);
 
 int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key);
@@ -49,23 +49,24 @@ int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync
 extern int bit_wait(struct wait_bit_key *key, int mode);
 extern int bit_wait_io(struct wait_bit_key *key, int mode);
 extern int bit_wait_timeout(struct wait_bit_key *key, int mode);
-extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * @word: the address containing the bit being waited on
+ * @bit: the bit at that address being waited on
  * @mode: the task state to sleep in
  *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit.
- * For instance, if one were to have waiters on a bitflag, one would
- * call wait_on_bit() in threads waiting for the bit to clear.
- * One uses wait_on_bit() where one is waiting for the bit to clear,
- * but has no intention of setting it.
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
+ * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP())
+ * to be cleared.  The clearing of the bit must be signalled with
+ * wake_up_bit(), often as clear_and_wake_up_bit().
+ *
+ * The process will wait on a waitqueue selected by hash from a shared
+ * pool.  It will only be woken on a wake_up for the target bit, even
+ * if other processes on the same queue are waiting for other bits.
+ *
+ * Returned value will be zero if the bit was cleared in which case the
+ * call has ACQUIRE semantics, or %-EINTR if the process received a
+ * signal and the mode permitted wake up on that signal.
  */
 static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
@@ -80,17 +81,20 @@ wait_on_bit(unsigned long *word, int bit, unsigned mode)
 
 /**
  * wait_on_bit_io - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * @word: the address containing the bit being waited on
+ * @bit: the bit at that address being waited on
  * @mode: the task state to sleep in
  *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared.  This is similar to wait_on_bit(), but calls
- * io_schedule() instead of schedule() for the actual waiting.
+ * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP())
+ * to be cleared.  The clearing of the bit must be signalled with
+ * wake_up_bit(), often as clear_and_wake_up_bit().
  *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
+ * This is similar to wait_on_bit(), but calls io_schedule() instead of
+ * schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared in which case the
+ * call has ACQUIRE semantics, or %-EINTR if the process received a
+ * signal and the mode permitted wake up on that signal.
  */
 static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
@@ -104,19 +108,24 @@ wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 }
 
 /**
- * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * wait_on_bit_timeout - wait for a bit to be cleared or a timeout to elapse
+ * @word: the address containing the bit being waited on
+ * @bit: the bit at that address being waited on
  * @mode: the task state to sleep in
  * @timeout: timeout, in jiffies
  *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared. This is similar to wait_on_bit(), except also takes a
- * timeout parameter.
+ * Wait for the given bit in an unsigned long or bitmap (see
+ * DECLARE_BITMAP()) to be cleared, or for a timeout to expire.  The
+ * clearing of the bit must be signalled with wake_up_bit(), often as
+ * clear_and_wake_up_bit().
+ *
+ * This is similar to wait_on_bit(), except it also takes a timeout
+ * parameter.
  *
- * Returned value will be zero if the bit was cleared before the
- * @timeout elapsed, or non-zero if the @timeout elapsed or process
- * received a signal and the mode permitted wakeup on that signal.
+ * Returned value will be zero if the bit was cleared in which case the
+ * call has ACQUIRE semantics, or %-EINTR if the process received a
+ * signal and the mode permitted wake up on that signal, or %-EAGAIN if the
+ * timeout elapsed.
  */
 static inline int
 wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
@@ -132,19 +141,21 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
 
 /**
  * wait_on_bit_action - wait for a bit to be cleared
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * @word: the address containing the bit waited on
+ * @bit: the bit at that address being waited on
  * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared, and allow the waiting action to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
+ * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP())
+ * to be cleared.  The clearing of the bit must be signalled with
+ * wake_up_bit(), often as clear_and_wake_up_bit().
+ *
+ * This is similar to wait_on_bit(), but calls @action() instead of
+ * schedule() for the actual waiting.
  *
- * Returned value will be zero if the bit was cleared, or non-zero
- * if the process received a signal and the mode permitted wakeup
- * on that signal.
+ * Returned value will be zero if the bit was cleared in which case the
+ * call has ACQUIRE semantics, or the error code returned by @action if
+ * that call returned non-zero.
  */
 static inline int
 wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
@@ -157,23 +168,22 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
 }
 
 /**
- * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * wait_on_bit_lock - wait for a bit to be cleared, then set it
+ * @word: the address containing the bit being waited on
+ * @bit: the bit of the word being waited on and set
  * @mode: the task state to sleep in
  *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that waits on a bit
- * when one intends to set it, for instance, trying to lock bitflags.
- * For instance, if one were to have waiters trying to set bitflag
- * and waiting for it to clear before setting it, one would call
- * wait_on_bit() in threads waiting to be able to set the bit.
- * One uses wait_on_bit_lock() where one is waiting for the bit to
- * clear with the intention of setting it, and when done, clearing it.
+ * Wait for the given bit in an unsigned long or bitmap (see
+ * DECLARE_BITMAP()) to be cleared.  The clearing of the bit must be
+ * signalled with wake_up_bit(), often as clear_and_wake_up_bit().  As
+ * soon as it is clear, atomically set it and return.
  *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
+ * This is similar to wait_on_bit(), but sets the bit before returning.
+ *
+ * Returned value will be zero if the bit was successfully set in which
+ * case the call has the same memory sequencing semantics as
+ * test_and_clear_bit(), or %-EINTR if the process received a signal and
+ * the mode permitted wake up on that signal.
  */
 static inline int
 wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
@@ -185,15 +195,18 @@ wait_on_bit_lock(unsigned long *word, int bit, unsigned mode)
 }
 
 /**
- * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * wait_on_bit_lock_io - wait for a bit to be cleared, then set it
+ * @word: the address containing the bit being waited on
+ * @bit: the bit of the word being waited on and set
  * @mode: the task state to sleep in
  *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to atomically set it.  This is similar
- * to wait_on_bit(), but calls io_schedule() instead of schedule()
- * for the actual waiting.
+ * Wait for the given bit in an unsigned long or bitmap (see
+ * DECLARE_BITMAP()) to be cleared.  The clearing of the bit must be
+ * signalled with wake_up_bit(), often as clear_and_wake_up_bit().  As
+ * soon as it is clear, atomically set it and return.
+ *
+ * This is similar to wait_on_bit_lock(), but calls io_schedule() instead
+ * of schedule().
  *
  * Returns zero if the bit was (eventually) found to be clear and was
  * set.  Returns non-zero if a signal was delivered to the process and
@@ -209,21 +222,19 @@ wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode)
 }
 
 /**
- * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
+ * wait_on_bit_lock_action - wait for a bit to be cleared, then set it
+ * @word: the address containing the bit being waited on
+ * @bit: the bit of the word being waited on and set
  * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
- * Use the standard hashed waitqueue table to wait for a bit
- * to be cleared and then to set it, and allow the waiting action
- * to be specified.
- * This is like wait_on_bit() but allows fine control of how the waiting
- * is done.
+ * This is similar to wait_on_bit_lock(), but calls @action() instead of
+ * schedule() for the actual waiting.
  *
- * Returns zero if the bit was (eventually) found to be clear and was
- * set.  Returns non-zero if a signal was delivered to the process and
- * the @mode allows that signal to wake the process.
+ * Returned value will be zero if the bit was successfully set in which
+ * case the call has the same memory sequencing semantics as
+ * test_and_clear_bit(), or the error code returned by @action if that
+ * call returned non-zero.
  */
 static inline int
 wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
@@ -269,7 +280,26 @@ __out:	__ret;								\
 #define __wait_var_event(var, condition)				\
 	___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			  schedule())
+#define __wait_var_event_io(var, condition)				\
+	___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			  io_schedule())
 
+/**
+ * wait_var_event - wait for a variable to be updated and notified
+ * @var: the address of variable being waited on
+ * @condition: the condition to wait for
+ *
+ * Wait for a @condition to be true, only re-checking when a wake up is
+ * received for the given @var (an arbitrary kernel address which need
+ * not be directly related to the given condition, but usually is).
+ *
+ * The process will wait on a waitqueue selected by hash from a shared
+ * pool.  It will only be woken on a wake_up for the given address.
+ *
+ * The condition should normally use smp_load_acquire() or a similarly
+ * ordered access to ensure that any changes to memory made before the
+ * condition became true will be visible after the wait completes.
+ */
 #define wait_var_event(var, condition)					\
 do {									\
 	might_sleep();							\
@@ -278,10 +308,56 @@ do {									\
 	__wait_var_event(var, condition);				\
 } while (0)
 
+/**
+ * wait_var_event_io - wait for a variable to be updated and notified
+ * @var: the address of variable being waited on
+ * @condition: the condition to wait for
+ *
+ * Wait for an IO related @condition to be true, only re-checking when a
+ * wake up is received for the given @var (an arbitrary kernel address
+ * which need not be directly related to the given condition, but
+ * usually is).
+ *
+ * The process will wait on a waitqueue selected by hash from a shared
+ * pool.  It will only be woken on a wake_up for the given address.
+ *
+ * This is similar to wait_var_event(), but calls io_schedule() instead
+ * of schedule().
+ *
+ * The condition should normally use smp_load_acquire() or a similarly
+ * ordered access to ensure that any changes to memory made before the
+ * condition became true will be visible after the wait completes.
+ */
+#define wait_var_event_io(var, condition)				\
+do {									\
+	might_sleep();							\
+	if (condition)							\
+		break;							\
+	__wait_var_event_io(var, condition);				\
+} while (0)
+
 #define __wait_var_event_killable(var, condition)			\
 	___wait_var_event(var, condition, TASK_KILLABLE, 0, 0,		\
 			  schedule())
 
+/**
+ * wait_var_event_killable - wait for a variable to be updated and notified
+ * @var: the address of variable being waited on
+ * @condition: the condition to wait for
+ *
+ * Wait for a @condition to be true or a fatal signal to be received,
+ * only re-checking the condition when a wake up is received for the given
+ * @var (an arbitrary kernel address which need not be directly related
+ * to the given condition, but usually is).
+ *
+ * This is similar to wait_var_event() but returns a value which is
+ * 0 if the condition became true, or %-ERESTARTSYS if a fatal signal
+ * was received.
+ *
+ * The condition should normally use smp_load_acquire() or a similarly
+ * ordered access to ensure that any changes to memory made before the
+ * condition became true will be visible after the wait completes.
+ */
 #define wait_var_event_killable(var, condition)				\
 ({									\
 	int __ret = 0;							\
@@ -296,6 +372,26 @@ do {									\
 			  TASK_UNINTERRUPTIBLE, 0, timeout,		\
 			  __ret = schedule_timeout(__ret))
 
+/**
+ * wait_var_event_timeout - wait for a variable to be updated or a timeout to expire
+ * @var: the address of variable being waited on
+ * @condition: the condition to wait for
+ * @timeout: maximum time to wait in jiffies
+ *
+ * Wait for a @condition to be true or a timeout to expire, only
+ * re-checking the condition when a wake up is received for the given
+ * @var (an arbitrary kernel address which need not be directly related
+ * to the given condition, but usually is).
+ *
+ * This is similar to wait_var_event() but returns a value which is 0 if
+ * the timeout expired and the condition was still false, or the
+ * remaining time left in the timeout (but at least 1) if the condition
+ * was found to be true.
+ *
+ * The condition should normally use smp_load_acquire() or a similarly
+ * ordered access to ensure that any changes to memory made before the
+ * condition became true will be visible after the wait completes.
+ */
 #define wait_var_event_timeout(var, condition, timeout)			\
 ({									\
 	long __ret = timeout;						\
@@ -309,6 +405,23 @@ do {									\
 	___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0,	\
 			  schedule())
 
+/**
+ * wait_var_event_killable - wait for a variable to be updated and notified
+ * @var: the address of variable being waited on
+ * @condition: the condition to wait for
+ *
+ * Wait for a @condition to be true or a signal to be received, only
+ * re-checking the condition when a wake up is received for the given
+ * @var (an arbitrary kernel address which need not be directly related
+ * to the given condition, but usually is).
+ *
+ * This is similar to wait_var_event() but returns a value which is 0 if
+ * the condition became true, or %-ERESTARTSYS if a signal was received.
+ *
+ * The condition should normally use smp_load_acquire() or a similarly
+ * ordered access to ensure that any changes to memory made before the
+ * condition became true will be visible after the wait completes.
+ */
 #define wait_var_event_interruptible(var, condition)			\
 ({									\
 	int __ret = 0;							\
@@ -319,15 +432,122 @@ do {									\
 })
 
 /**
- * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit
+ * wait_var_event_any_lock - wait for a variable to be updated under a lock
+ * @var: the address of the variable being waited on
+ * @condition: condition to wait for
+ * @lock: the object that is locked to protect updates to the variable
+ * @type: prefix on lock and unlock operations
+ * @state: waiting state, %TASK_UNINTERRUPTIBLE etc.
+ *
+ * Wait for a condition which can only be reliably tested while holding
+ * a lock.  The variables assessed in the condition will normal be updated
+ * under the same lock, and the wake up should be signalled with
+ * wake_up_var_locked() under the same lock.
+ *
+ * This is similar to wait_var_event(), but assumes a lock is held
+ * while calling this function and while updating the variable.
  *
+ * This must be called while the given lock is held and the lock will be
+ * dropped when schedule() is called to wait for a wake up, and will be
+ * reclaimed before testing the condition again.  The functions used to
+ * unlock and lock the object are constructed by appending _unlock and _lock
+ * to @type.
+ *
+ * Return %-ERESTARTSYS if a signal arrives which is allowed to interrupt
+ * the wait according to @state.
+ */
+#define wait_var_event_any_lock(var, condition, lock, type, state)	\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__ret = ___wait_var_event(var, condition, state, 0, 0,	\
+					  type ## _unlock(lock);	\
+					  schedule();			\
+					  type ## _lock(lock));		\
+	__ret;								\
+})
+
+/**
+ * wait_var_event_spinlock - wait for a variable to be updated under a spinlock
+ * @var: the address of the variable being waited on
+ * @condition: condition to wait for
+ * @lock: the spinlock which protects updates to the variable
+ *
+ * Wait for a condition which can only be reliably tested while holding
+ * a spinlock.  The variables assessed in the condition will normal be updated
+ * under the same spinlock, and the wake up should be signalled with
+ * wake_up_var_locked() under the same spinlock.
+ *
+ * This is similar to wait_var_event(), but assumes a spinlock is held
+ * while calling this function and while updating the variable.
+ *
+ * This must be called while the given lock is held and the lock will be
+ * dropped when schedule() is called to wait for a wake up, and will be
+ * reclaimed before testing the condition again.
+ */
+#define wait_var_event_spinlock(var, condition, lock)			\
+	wait_var_event_any_lock(var, condition, lock, spin, TASK_UNINTERRUPTIBLE)
+
+/**
+ * wait_var_event_mutex - wait for a variable to be updated under a mutex
+ * @var: the address of the variable being waited on
+ * @condition: condition to wait for
+ * @mutex: the mutex which protects updates to the variable
+ *
+ * Wait for a condition which can only be reliably tested while holding
+ * a mutex.  The variables assessed in the condition will normal be
+ * updated under the same mutex, and the wake up should be signalled
+ * with wake_up_var_locked() under the same mutex.
+ *
+ * This is similar to wait_var_event(), but assumes a mutex is held
+ * while calling this function and while updating the variable.
+ *
+ * This must be called while the given mutex is held and the mutex will be
+ * dropped when schedule() is called to wait for a wake up, and will be
+ * reclaimed before testing the condition again.
+ */
+#define wait_var_event_mutex(var, condition, lock)			\
+	wait_var_event_any_lock(var, condition, lock, mutex, TASK_UNINTERRUPTIBLE)
+
+/**
+ * wake_up_var_protected - wake up waiters for a variable asserting that it is safe
+ * @var: the address of the variable being waited on
+ * @cond: the condition which afirms this is safe
+ *
+ * When waking waiters which use wait_var_event_any_lock() the waker must be
+ * holding the reelvant lock to avoid races.  This version of wake_up_var()
+ * asserts that the relevant lock is held and so no barrier is needed.
+ * The @cond is only tested when CONFIG_LOCKDEP is enabled.
+ */
+#define wake_up_var_protected(var, cond)				\
+do {									\
+	lockdep_assert(cond);						\
+	wake_up_var(var);						\
+} while (0)
+
+/**
+ * wake_up_var_locked - wake up waiters for a variable while holding a spinlock or mutex
+ * @var: the address of the variable being waited on
+ * @lock: The spinlock or mutex what protects the variable
+ *
+ * Send a wake up for the given variable which should be waited for with
+ * wait_var_event_spinlock() or wait_var_event_mutex().  Unlike wake_up_var(),
+ * no extra barriers are needed as the locking provides sufficient sequencing.
+ */
+#define wake_up_var_locked(var, lock)					\
+	wake_up_var_protected(var, lockdep_is_held(lock))
+
+/**
+ * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit
  * @bit: the bit of the word being waited on
- * @word: the word being waited on, a kernel virtual address
+ * @word: the address containing the bit being waited on
  *
- * You can use this helper if bitflags are manipulated atomically rather than
- * non-atomically under a lock.
+ * The designated bit is cleared and any tasks waiting in wait_on_bit()
+ * or similar will be woken.  This call has RELEASE semantics so that
+ * any changes to memory made before this call are guaranteed to be visible
+ * after the corresponding wait_on_bit() completes.
  */
-static inline void clear_and_wake_up_bit(int bit, void *word)
+static inline void clear_and_wake_up_bit(int bit, unsigned long *word)
 {
 	clear_bit_unlock(bit, word);
 	/* See wake_up_bit() for which memory barrier you need to use. */
@@ -335,4 +555,64 @@ static inline void clear_and_wake_up_bit(int bit, void *word)
 	wake_up_bit(word, bit);
 }
 
+/**
+ * test_and_clear_wake_up_bit - clear a bit if it was set: wake up anyone waiting on that bit
+ * @bit: the bit of the word being waited on
+ * @word: the address of memory containing that bit
+ *
+ * If the bit is set and can be atomically cleared, any tasks waiting in
+ * wait_on_bit() or similar will be woken.  This call has the same
+ * complete ordering semantics as test_and_clear_bit().  Any changes to
+ * memory made before this call are guaranteed to be visible after the
+ * corresponding wait_on_bit() completes.
+ *
+ * Returns %true if the bit was successfully set and the wake up was sent.
+ */
+static inline bool test_and_clear_wake_up_bit(int bit, unsigned long *word)
+{
+	if (!test_and_clear_bit(bit, word))
+		return false;
+	/* no extra barrier required */
+	wake_up_bit(word, bit);
+	return true;
+}
+
+/**
+ * atomic_dec_and_wake_up - decrement an atomic_t and if zero, wake up waiters
+ * @var: the variable to dec and test
+ *
+ * Decrements the atomic variable and if it reaches zero, send a wake_up to any
+ * processes waiting on the variable.
+ *
+ * This function has the same complete ordering semantics as atomic_dec_and_test.
+ *
+ * Returns %true is the variable reaches zero and the wake up was sent.
+ */
+
+static inline bool atomic_dec_and_wake_up(atomic_t *var)
+{
+	if (!atomic_dec_and_test(var))
+		return false;
+	/* No extra barrier required */
+	wake_up_var(var);
+	return true;
+}
+
+/**
+ * store_release_wake_up - update a variable and send a wake_up
+ * @var: the address of the variable to be updated and woken
+ * @val: the value to store in the variable.
+ *
+ * Store the given value in the variable send a wake up to any tasks
+ * waiting on the variable.  All necessary barriers are included to ensure
+ * the task calling wait_var_event() sees the new value and all values
+ * written to memory before this call.
+ */
+#define store_release_wake_up(var, val)					\
+do {									\
+	smp_store_release(var, val);					\
+	smp_mb();							\
+	wake_up_var(var);						\
+} while (0)
+
 #endif /* _LINUX_WAIT_BIT_H */