Merge branch 'WIP.locking/seqlocks' into locking/urgent

Pick up the full seqlock series PeterZ is working on.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 752 insertions, 263 deletions

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 8b97204f35a7..a076f783aa36 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -1,48 +1,31 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_SEQLOCK_H
 #define __LINUX_SEQLOCK_H
+
 /*
- * Reader/writer consistent mechanism without starving writers. This type of
- * lock for data where the reader wants a consistent set of information
- * and is willing to retry if the information changes. There are two types
- * of readers:
- * 1. Sequence readers which never block a writer but they may have to retry
- *    if a writer is in progress by detecting change in sequence number.
- *    Writers do not wait for a sequence reader.
- * 2. Locking readers which will wait if a writer or another locking reader
- *    is in progress. A locking reader in progress will also block a writer
- *    from going forward. Unlike the regular rwlock, the read lock here is
- *    exclusive so that only one locking reader can get it.
- *
- * This is not as cache friendly as brlock. Also, this may not work well
- * for data that contains pointers, because any writer could
- * invalidate a pointer that a reader was following.
- *
- * Expected non-blocking reader usage:
- * 	do {
- *	    seq = read_seqbegin(&foo);
- * 	...
- *      } while (read_seqretry(&foo, seq));
+ * seqcount_t / seqlock_t - a reader-writer consistency mechanism with
+ * lockless readers (read-only retry loops), and no writer starvation.
  *
+ * See Documentation/locking/seqlock.rst
  *
- * On non-SMP the spin locks disappear but the writer still needs
- * to increment the sequence variables because an interrupt routine could
- * change the state of the data.
- *
- * Based on x86_64 vsyscall gettimeofday 
- * by Keith Owens and Andrea Arcangeli
+ * Copyrights:
+ * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli
+ * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH
  */
 
-#include <linux/spinlock.h>
-#include <linux/preempt.h>
-#include <linux/lockdep.h>
 #include <linux/compiler.h>
 #include <linux/kcsan-checks.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/ww_mutex.h>
+
 #include <asm/processor.h>
 
 /*
- * The seqlock interface does not prescribe a precise sequence of read
- * begin/retry/end. For readers, typically there is a call to
+ * The seqlock seqcount_t interface does not prescribe a precise sequence of
+ * read begin/retry/end. For readers, typically there is a call to
  * read_seqcount_begin() and read_seqcount_retry(), however, there are more
  * esoteric cases which do not follow this pattern.
  *
@@ -50,16 +33,34 @@
  * via seqcount_t under KCSAN: upon beginning a seq-reader critical section,
  * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as
  * atomics; if there is a matching read_seqcount_retry() call, no following
- * memory operations are considered atomic. Usage of seqlocks via seqlock_t
- * interface is not affected.
+ * memory operations are considered atomic. Usage of the seqlock_t interface
+ * is not affected.
  */
 #define KCSAN_SEQLOCK_REGION_MAX 1000
 
 /*
- * Version using sequence counter only.
- * This can be used when code has its own mutex protecting the
- * updating starting before the write_seqcountbeqin() and ending
- * after the write_seqcount_end().
+ * Sequence counters (seqcount_t)
+ *
+ * This is the raw counting mechanism, without any writer protection.
+ *
+ * Write side critical sections must be serialized and non-preemptible.
+ *
+ * If readers can be invoked from hardirq or softirq contexts,
+ * interrupts or bottom halves must also be respectively disabled before
+ * entering the write section.
+ *
+ * This mechanism can't be used if the protected data contains pointers,
+ * as the writer can invalidate a pointer that a reader is following.
+ *
+ * If the write serialization mechanism is one of the common kernel
+ * locking primitives, use a sequence counter with associated lock
+ * (seqcount_LOCKTYPE_t) instead.
+ *
+ * If it's desired to automatically handle the sequence counter writer
+ * serialization and non-preemptibility requirements, use a sequential
+ * lock (seqlock_t) instead.
+ *
+ * See Documentation/locking/seqlock.rst
  */
 typedef struct seqcount {
 	unsigned sequence;
@@ -79,13 +80,18 @@ static inline void __seqcount_init(seqcount_t *s, const char *name,
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SEQCOUNT_DEP_MAP_INIT(lockname) \
-		.dep_map = { .name = #lockname } \
 
-# define seqcount_init(s)				\
-	do {						\
-		static struct lock_class_key __key;	\
-		__seqcount_init((s), #s, &__key);	\
+# define SEQCOUNT_DEP_MAP_INIT(lockname)				\
+		.dep_map = { .name = #lockname }
+
+/**
+ * seqcount_init() - runtime initializer for seqcount_t
+ * @s: Pointer to the seqcount_t instance
+ */
+# define seqcount_init(s)						\
+	do {								\
+		static struct lock_class_key __key;			\
+		__seqcount_init((s), #s, &__key);			\
 	} while (0)
 
 static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
@@ -105,13 +111,149 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 # define seqcount_lockdep_reader_access(x)
 #endif
 
-#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)}
+/**
+ * SEQCNT_ZERO() - static initializer for seqcount_t
+ * @name: Name of the seqcount_t instance
+ */
+#define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
+
+/*
+ * Sequence counters with associated locks (seqcount_LOCKTYPE_t)
+ *
+ * A sequence counter which associates the lock used for writer
+ * serialization at initialization time. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ *
+ * For associated locks which do not implicitly disable preemption,
+ * preemption protection is enforced in the write side function.
+ *
+ * Lockdep is never used in any for the raw write variants.
+ *
+ * See Documentation/locking/seqlock.rst
+ */
+
+#ifdef CONFIG_LOCKDEP
+#define __SEQ_LOCK(expr)	expr
+#else
+#define __SEQ_LOCK(expr)
+#endif
+
+/**
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated
+ * @seqcount:	The real sequence counter
+ * @lock:	Pointer to the associated spinlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * spinlock. The spinlock is associated to the sequence count in the
+ * static initializer or init function. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ */
+
+/**
+ * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
+ * @s:		Pointer to the seqcount_LOCKNAME_t instance
+ * @lock:	Pointer to the associated LOCKTYPE
+ */
+
+/*
+ * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
+ * @locktype:		actual typename
+ * @lockname:		name
+ * @preemptible:	preemptibility of above locktype
+ * @lockmember:		argument for lockdep_assert_held()
+ */
+#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember)	\
+typedef struct seqcount_##lockname {					\
+	seqcount_t		seqcount;				\
+	__SEQ_LOCK(locktype	*lock);					\
+} seqcount_##lockname##_t;						\
+									\
+static __always_inline void						\
+seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
+{									\
+	seqcount_init(&s->seqcount);					\
+	__SEQ_LOCK(s->lock = lock);					\
+}									\
+									\
+static __always_inline seqcount_t *					\
+__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s)			\
+{									\
+	return &s->seqcount;						\
+}									\
+									\
+static __always_inline bool						\
+__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s)		\
+{									\
+	return preemptible;						\
+}									\
+									\
+static __always_inline void						\
+__seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
+{									\
+	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
+}
+
+/*
+ * __seqprop() for seqcount_t
+ */
+
+static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
+{
+	return s;
+}
+
+static inline bool __seqcount_preemptible(seqcount_t *s)
+{
+	return false;
+}
+
+static inline void __seqcount_assert(seqcount_t *s)
+{
+	lockdep_assert_preemption_disabled();
+}
+
+SEQCOUNT_LOCKTYPE(raw_spinlock_t,	raw_spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(spinlock_t,		spinlock,	false,	s->lock)
+SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
+SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
+SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
+
+/**
+ * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
+ * @name:	Name of the seqcount_LOCKNAME_t instance
+ * @lock:	Pointer to the associated LOCKTYPE
+ */
+
+#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
+	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
+	__SEQ_LOCK(.lock	= (assoc_lock))				\
+}
+
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
 
 
+#define __seqprop_case(s, lockname, prop)				\
+	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
+
+#define __seqprop(s, prop) _Generic(*(s),				\
+	seqcount_t:		__seqcount_##prop((void *)(s)),		\
+	__seqprop_case((s),	raw_spinlock,	prop),			\
+	__seqprop_case((s),	spinlock,	prop),			\
+	__seqprop_case((s),	rwlock,		prop),			\
+	__seqprop_case((s),	mutex,		prop),			\
+	__seqprop_case((s),	ww_mutex,	prop))
+
+#define __seqcount_ptr(s)		__seqprop(s, ptr)
+#define __seqcount_lock_preemptible(s)	__seqprop(s, preemptible)
+#define __seqcount_assert_lock_held(s)	__seqprop(s, assert)
+
 /**
- * __read_seqcount_begin - begin a seq-read critical section (without barrier)
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -120,8 +262,13 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  *
  * Use carefully, only in critical code, and comment how the barrier is
  * provided.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned __read_seqcount_begin(const seqcount_t *s)
+#define __read_seqcount_begin(s)					\
+	__read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
 {
 	unsigned ret;
 
@@ -136,80 +283,91 @@ repeat:
 }
 
 /**
- * raw_read_seqcount - Read the raw seqcount
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
- * raw_read_seqcount opens a read critical section of the given
- * seqcount without any lockdep checking and without checking or
- * masking the LSB. Calling code is responsible for handling that.
+ * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_read_seqcount(const seqcount_t *s)
+#define raw_read_seqcount_begin(s)					\
+	raw_read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
 {
-	unsigned ret = READ_ONCE(s->sequence);
+	unsigned ret = __read_seqcount_t_begin(s);
 	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
 	return ret;
 }
 
 /**
- * raw_read_seqcount_begin - start seq-read critical section w/o lockdep
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * read_seqcount_begin() - begin a seqcount_t read critical section
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
- * raw_read_seqcount_begin opens a read critical section of the given
- * seqcount, but without any lockdep checking. Validity of the critical
- * section is tested by checking read_seqcount_retry function.
+ * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
+#define read_seqcount_begin(s)						\
+	read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
 {
-	unsigned ret = __read_seqcount_begin(s);
-	smp_rmb();
-	return ret;
+	seqcount_lockdep_reader_access(s);
+	return raw_read_seqcount_t_begin(s);
 }
 
 /**
- * read_seqcount_begin - begin a seq-read critical section
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_read_seqcount() - read the raw seqcount_t counter value
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
- * read_seqcount_begin opens a read critical section of the given seqcount.
- * Validity of the critical section is tested by checking read_seqcount_retry
- * function.
+ * raw_read_seqcount opens a read critical section of the given
+ * seqcount_t, without any lockdep checking, and without checking or
+ * masking the sequence counter LSB. Calling code is responsible for
+ * handling that.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned read_seqcount_begin(const seqcount_t *s)
+#define raw_read_seqcount(s)						\
+	raw_read_seqcount_t(__seqcount_ptr(s))
+
+static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
 {
-	seqcount_lockdep_reader_access(s);
-	return raw_read_seqcount_begin(s);
+	unsigned ret = READ_ONCE(s->sequence);
+	smp_rmb();
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
+	return ret;
 }
 
 /**
- * raw_seqcount_begin - begin a seq-read critical section
- * @s: pointer to seqcount_t
- * Returns: count to be passed to read_seqcount_retry
+ * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
+ *                        lockdep and w/o counter stabilization
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
- * raw_seqcount_begin opens a read critical section of the given seqcount.
- * Validity of the critical section is tested by checking read_seqcount_retry
- * function.
+ * raw_seqcount_begin opens a read critical section of the given
+ * seqcount_t. Unlike read_seqcount_begin(), this function will not wait
+ * for the count to stabilize. If a writer is active when it begins, it
+ * will fail the read_seqcount_retry() at the end of the read critical
+ * section instead of stabilizing at the beginning of it.
  *
- * Unlike read_seqcount_begin(), this function will not wait for the count
- * to stabilize. If a writer is active when we begin, we will fail the
- * read_seqcount_retry() instead of stabilizing at the beginning of the
- * critical section.
+ * Use this only in special kernel hot paths where the read section is
+ * small and has a high probability of success through other external
+ * means. It will save a single branching instruction.
+ *
+ * Return: count to be passed to read_seqcount_retry()
  */
-static inline unsigned raw_seqcount_begin(const seqcount_t *s)
+#define raw_seqcount_begin(s)						\
+	raw_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
 {
-	unsigned ret = READ_ONCE(s->sequence);
-	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret & ~1;
+	/*
+	 * If the counter is odd, let read_seqcount_retry() fail
+	 * by decrementing the counter.
+	 */
+	return raw_read_seqcount_t(s) & ~1;
 }
 
 /**
- * __read_seqcount_retry - end a seq-read critical section (without barrier)
- * @s: pointer to seqcount_t
- * @start: count, from read_seqcount_begin
- * Returns: 1 if retry is required, else 0
+ * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @start: count, from read_seqcount_begin()
  *
  * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -218,39 +376,70 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
  *
  * Use carefully, only in critical code, and comment how the barrier is
  * provided.
+ *
+ * Return: true if a read section retry is required, else false
  */
-static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define __read_seqcount_retry(s, start)					\
+	__read_seqcount_t_retry(__seqcount_ptr(s), start)
+
+static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
 	kcsan_atomic_next(0);
 	return unlikely(READ_ONCE(s->sequence) != start);
 }
 
 /**
- * read_seqcount_retry - end a seq-read critical section
- * @s: pointer to seqcount_t
- * @start: count, from read_seqcount_begin
- * Returns: 1 if retry is required, else 0
+ * read_seqcount_retry() - end a seqcount_t read critical section
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @start: count, from read_seqcount_begin()
  *
- * read_seqcount_retry closes a read critical section of the given seqcount.
- * If the critical section was invalid, it must be ignored (and typically
- * retried).
+ * read_seqcount_retry closes the read critical section of given
+ * seqcount_t.  If the critical section was invalid, it must be ignored
+ * (and typically retried).
+ *
+ * Return: true if a read section retry is required, else false
  */
-static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define read_seqcount_retry(s, start)					\
+	read_seqcount_t_retry(__seqcount_ptr(s), start)
+
+static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 {
 	smp_rmb();
-	return __read_seqcount_retry(s, start);
+	return __read_seqcount_t_retry(s, start);
 }
 
-
-
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+/**
+ * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ */
+#define raw_write_seqcount_begin(s)					\
+do {									\
+	if (__seqcount_lock_preemptible(s))				\
+		preempt_disable();					\
+									\
+	raw_write_seqcount_t_begin(__seqcount_ptr(s));			\
+} while (0)
+
+static inline void raw_write_seqcount_t_begin(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
 	smp_wmb();
 }
 
-static inline void raw_write_seqcount_end(seqcount_t *s)
+/**
+ * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ */
+#define raw_write_seqcount_end(s)					\
+do {									\
+	raw_write_seqcount_t_end(__seqcount_ptr(s));			\
+									\
+	if (__seqcount_lock_preemptible(s))				\
+		preempt_enable();					\
+} while (0)
+
+static inline void raw_write_seqcount_t_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
@@ -258,47 +447,120 @@ static inline void raw_write_seqcount_end(seqcount_t *s)
 }
 
 /**
- * raw_write_seqcount_barrier - do a seq write barrier
- * @s: pointer to seqcount_t
+ * write_seqcount_begin_nested() - start a seqcount_t write section with
+ *                                 custom lockdep nesting level
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @subclass: lockdep nesting level
+ *
+ * See Documentation/locking/lockdep-design.rst
+ */
+#define write_seqcount_begin_nested(s, subclass)			\
+do {									\
+	__seqcount_assert_lock_held(s);					\
+									\
+	if (__seqcount_lock_preemptible(s))				\
+		preempt_disable();					\
+									\
+	write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass);	\
+} while (0)
+
+static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
+{
+	raw_write_seqcount_t_begin(s);
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+}
+
+/**
+ * write_seqcount_begin() - start a seqcount_t write side critical section
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ *
+ * write_seqcount_begin opens a write side critical section of the given
+ * seqcount_t.
+ *
+ * Context: seqcount_t write side critical sections must be serialized and
+ * non-preemptible. If readers can be invoked from hardirq or softirq
+ * context, interrupts or bottom halves must be respectively disabled.
+ */
+#define write_seqcount_begin(s)						\
+do {									\
+	__seqcount_assert_lock_held(s);					\
+									\
+	if (__seqcount_lock_preemptible(s))				\
+		preempt_disable();					\
+									\
+	write_seqcount_t_begin(__seqcount_ptr(s));			\
+} while (0)
+
+static inline void write_seqcount_t_begin(seqcount_t *s)
+{
+	write_seqcount_t_begin_nested(s, 0);
+}
+
+/**
+ * write_seqcount_end() - end a seqcount_t write side critical section
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
- * This can be used to provide an ordering guarantee instead of the
- * usual consistency guarantee. It is one wmb cheaper, because we can
- * collapse the two back-to-back wmb()s.
+ * The write section must've been opened with write_seqcount_begin().
+ */
+#define write_seqcount_end(s)						\
+do {									\
+	write_seqcount_t_end(__seqcount_ptr(s));			\
+									\
+	if (__seqcount_lock_preemptible(s))				\
+		preempt_enable();					\
+} while (0)
+
+static inline void write_seqcount_t_end(seqcount_t *s)
+{
+	seqcount_release(&s->dep_map, _RET_IP_);
+	raw_write_seqcount_t_end(s);
+}
+
+/**
+ * raw_write_seqcount_barrier() - do a seqcount_t write barrier
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ *
+ * This can be used to provide an ordering guarantee instead of the usual
+ * consistency guarantee. It is one wmb cheaper, because it can collapse
+ * the two back-to-back wmb()s.
  *
  * Note that writes surrounding the barrier should be declared atomic (e.g.
  * via WRITE_ONCE): a) to ensure the writes become visible to other threads
  * atomically, avoiding compiler optimizations; b) to document which writes are
  * meant to propagate to the reader critical section. This is necessary because
  * neither writes before and after the barrier are enclosed in a seq-writer
- * critical section that would ensure readers are aware of ongoing writes.
+ * critical section that would ensure readers are aware of ongoing writes::
  *
- *      seqcount_t seq;
- *      bool X = true, Y = false;
+ *	seqcount_t seq;
+ *	bool X = true, Y = false;
  *
- *      void read(void)
- *      {
- *              bool x, y;
+ *	void read(void)
+ *	{
+ *		bool x, y;
  *
- *              do {
- *                      int s = read_seqcount_begin(&seq);
+ *		do {
+ *			int s = read_seqcount_begin(&seq);
  *
- *                      x = X; y = Y;
+ *			x = X; y = Y;
  *
- *              } while (read_seqcount_retry(&seq, s));
+ *		} while (read_seqcount_retry(&seq, s));
  *
- *              BUG_ON(!x && !y);
+ *		BUG_ON(!x && !y);
  *      }
  *
  *      void write(void)
  *      {
- *              WRITE_ONCE(Y, true);
+ *		WRITE_ONCE(Y, true);
  *
- *              raw_write_seqcount_barrier(seq);
+ *		raw_write_seqcount_barrier(seq);
  *
- *              WRITE_ONCE(X, false);
+ *		WRITE_ONCE(X, false);
  *      }
  */
-static inline void raw_write_seqcount_barrier(seqcount_t *s)
+#define raw_write_seqcount_barrier(s)					\
+	raw_write_seqcount_t_barrier(__seqcount_ptr(s))
+
+static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 {
 	kcsan_nestable_atomic_begin();
 	s->sequence++;
@@ -307,7 +569,44 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
-static inline int raw_read_seqcount_latch(seqcount_t *s)
+/**
+ * write_seqcount_invalidate() - invalidate in-progress seqcount_t read
+ *                               side operations
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ *
+ * After write_seqcount_invalidate, no seqcount_t read side operations
+ * will complete successfully and see data older than this.
+ */
+#define write_seqcount_invalidate(s)					\
+	write_seqcount_t_invalidate(__seqcount_ptr(s))
+
+static inline void write_seqcount_t_invalidate(seqcount_t *s)
+{
+	smp_wmb();
+	kcsan_nestable_atomic_begin();
+	s->sequence+=2;
+	kcsan_nestable_atomic_end();
+}
+
+/**
+ * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ *
+ * Use seqcount_t latching to switch between two storage places protected
+ * by a sequence counter. Doing so allows having interruptible, preemptible,
+ * seqcount_t write side critical sections.
+ *
+ * Check raw_write_seqcount_latch() for more details and a full reader and
+ * writer usage example.
+ *
+ * Return: sequence counter raw value. Use the lowest bit as an index for
+ * picking which data copy to read. The full counter value must then be
+ * checked with read_seqcount_retry().
+ */
+#define raw_read_seqcount_latch(s)					\
+	raw_read_seqcount_t_latch(__seqcount_ptr(s))
+
+static inline int raw_read_seqcount_t_latch(seqcount_t *s)
 {
 	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
 	int seq = READ_ONCE(s->sequence); /* ^^^ */
@@ -315,8 +614,8 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
 }
 
 /**
- * raw_write_seqcount_latch - redirect readers to even/odd copy
- * @s: pointer to seqcount_t
+ * raw_write_seqcount_latch() - redirect readers to even/odd copy
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -332,66 +631,73 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
  * Very simply put: we first modify one copy and then the other. This ensures
  * there is always one copy in a stable state, ready to give us an answer.
  *
- * The basic form is a data structure like:
+ * The basic form is a data structure like::
  *
- * struct latch_struct {
- *	seqcount_t		seq;
- *	struct data_struct	data[2];
- * };
+ *	struct latch_struct {
+ *		seqcount_t		seq;
+ *		struct data_struct	data[2];
+ *	};
  *
  * Where a modification, which is assumed to be externally serialized, does the
- * following:
+ * following::
  *
- * void latch_modify(struct latch_struct *latch, ...)
- * {
- *	smp_wmb();	<- Ensure that the last data[1] update is visible
- *	latch->seq++;
- *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *	void latch_modify(struct latch_struct *latch, ...)
+ *	{
+ *		smp_wmb();	// Ensure that the last data[1] update is visible
+ *		latch->seq++;
+ *		smp_wmb();	// Ensure that the seqcount update is visible
  *
- *	modify(latch->data[0], ...);
+ *		modify(latch->data[0], ...);
  *
- *	smp_wmb();	<- Ensure that the data[0] update is visible
- *	latch->seq++;
- *	smp_wmb();	<- Ensure that the seqcount update is visible
+ *		smp_wmb();	// Ensure that the data[0] update is visible
+ *		latch->seq++;
+ *		smp_wmb();	// Ensure that the seqcount update is visible
  *
- *	modify(latch->data[1], ...);
- * }
+ *		modify(latch->data[1], ...);
+ *	}
  *
- * The query will have a form like:
+ * The query will have a form like::
  *
- * struct entry *latch_query(struct latch_struct *latch, ...)
- * {
- *	struct entry *entry;
- *	unsigned seq, idx;
+ *	struct entry *latch_query(struct latch_struct *latch, ...)
+ *	{
+ *		struct entry *entry;
+ *		unsigned seq, idx;
  *
- *	do {
- *		seq = raw_read_seqcount_latch(&latch->seq);
+ *		do {
+ *			seq = raw_read_seqcount_latch(&latch->seq);
  *
- *		idx = seq & 0x01;
- *		entry = data_query(latch->data[idx], ...);
+ *			idx = seq & 0x01;
+ *			entry = data_query(latch->data[idx], ...);
  *
- *		smp_rmb();
- *	} while (seq != latch->seq);
+ *		// read_seqcount_retry() includes needed smp_rmb()
+ *		} while (read_seqcount_retry(&latch->seq, seq));
  *
- *	return entry;
- * }
+ *		return entry;
+ *	}
  *
  * So during the modification, queries are first redirected to data[1]. Then we
  * modify data[0]. When that is complete, we redirect queries back to data[0]
  * and we can modify data[1].
  *
- * NOTE: The non-requirement for atomic modifications does _NOT_ include
- *       the publishing of new entries in the case where data is a dynamic
- *       data structure.
+ * NOTE:
+ *
+ *	The non-requirement for atomic modifications does _NOT_ include
+ *	the publishing of new entries in the case where data is a dynamic
+ *	data structure.
  *
- *       An iteration might start in data[0] and get suspended long enough
- *       to miss an entire modification sequence, once it resumes it might
- *       observe the new entry.
+ *	An iteration might start in data[0] and get suspended long enough
+ *	to miss an entire modification sequence, once it resumes it might
+ *	observe the new entry.
  *
- * NOTE: When data is a dynamic data structure; one should use regular RCU
- *       patterns to manage the lifetimes of the objects within.
+ * NOTE:
+ *
+ *	When data is a dynamic data structure; one should use regular RCU
+ *	patterns to manage the lifetimes of the objects within.
  */
-static inline void raw_write_seqcount_latch(seqcount_t *s)
+#define raw_write_seqcount_latch(s)					\
+	raw_write_seqcount_t_latch(__seqcount_ptr(s))
+
+static inline void raw_write_seqcount_t_latch(seqcount_t *s)
 {
        smp_wmb();      /* prior stores before incrementing "sequence" */
        s->sequence++;
@@ -399,67 +705,48 @@ static inline void raw_write_seqcount_latch(seqcount_t *s)
 }
 
 /*
- * Sequence counter only version assumes that callers are using their
- * own mutexing.
- */
-static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
-{
-	raw_write_seqcount_begin(s);
-	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
-}
-
-static inline void write_seqcount_begin(seqcount_t *s)
-{
-	write_seqcount_begin_nested(s, 0);
-}
-
-static inline void write_seqcount_end(seqcount_t *s)
-{
-	seqcount_release(&s->dep_map, _RET_IP_);
-	raw_write_seqcount_end(s);
-}
-
-/**
- * write_seqcount_invalidate - invalidate in-progress read-side seq operations
- * @s: pointer to seqcount_t
+ * Sequential locks (seqlock_t)
+ *
+ * Sequence counters with an embedded spinlock for writer serialization
+ * and non-preemptibility.
  *
- * After write_seqcount_invalidate, no read-side seq operations will complete
- * successfully and see data older than this.
+ * For more info, see:
+ *    - Comments on top of seqcount_t
+ *    - Documentation/locking/seqlock.rst
  */
-static inline void write_seqcount_invalidate(seqcount_t *s)
-{
-	smp_wmb();
-	kcsan_nestable_atomic_begin();
-	s->sequence+=2;
-	kcsan_nestable_atomic_end();
-}
-
 typedef struct {
 	struct seqcount seqcount;
 	spinlock_t lock;
 } seqlock_t;
 
-/*
- * These macros triggered gcc-3.x compile-time problems.  We think these are
- * OK now.  Be cautious.
- */
-#define __SEQLOCK_UNLOCKED(lockname)			\
-	{						\
-		.seqcount = SEQCNT_ZERO(lockname),	\
-		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
+#define __SEQLOCK_UNLOCKED(lockname)					\
+	{								\
+		.seqcount = SEQCNT_ZERO(lockname),			\
+		.lock =	__SPIN_LOCK_UNLOCKED(lockname)			\
 	}
 
-#define seqlock_init(x)					\
-	do {						\
-		seqcount_init(&(x)->seqcount);		\
-		spin_lock_init(&(x)->lock);		\
+/**
+ * seqlock_init() - dynamic initializer for seqlock_t
+ * @sl: Pointer to the seqlock_t instance
+ */
+#define seqlock_init(sl)						\
+	do {								\
+		seqcount_init(&(sl)->seqcount);				\
+		spin_lock_init(&(sl)->lock);				\
 	} while (0)
 
-#define DEFINE_SEQLOCK(x) \
-		seqlock_t x = __SEQLOCK_UNLOCKED(x)
+/**
+ * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t
+ * @sl: Name of the seqlock_t instance
+ */
+#define DEFINE_SEQLOCK(sl) \
+		seqlock_t sl = __SEQLOCK_UNLOCKED(sl)
 
-/*
- * Read side functions for starting and finalizing a read side section.
+/**
+ * read_seqbegin() - start a seqlock_t read side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * Return: count, to be passed to read_seqretry()
  */
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
@@ -470,6 +757,17 @@ static inline unsigned read_seqbegin(const seqlock_t *sl)
 	return ret;
 }
 
+/**
+ * read_seqretry() - end a seqlock_t read side section
+ * @sl: Pointer to seqlock_t
+ * @start: count, from read_seqbegin()
+ *
+ * read_seqretry closes the read side critical section of given seqlock_t.
+ * If the critical section was invalid, it must be ignored (and typically
+ * retried).
+ *
+ * Return: true if a read section retry is required, else false
+ */
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
 	/*
@@ -481,44 +779,88 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 	return read_seqcount_retry(&sl->seqcount, start);
 }
 
-/*
- * Lock out other writers and update the count.
- * Acts like a normal spin_lock/unlock.
- * Don't need preempt_disable() because that is in the spin_lock already.
+/**
+ * write_seqlock() - start a seqlock_t write side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_seqlock opens a write side critical section for the given
+ * seqlock_t.  It also implicitly acquires the spinlock_t embedded inside
+ * that sequential lock. All seqlock_t write side sections are thus
+ * automatically serialized and non-preemptible.
+ *
+ * Context: if the seqlock_t read section, or other write side critical
+ * sections, can be invoked from hardirq or softirq contexts, use the
+ * _irqsave or _bh variants of this function instead.
  */
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount);
 }
 
+/**
+ * write_sequnlock() - end a seqlock_t write side critical section
+ * @sl: Pointer to seqlock_t
+ *
+ * write_sequnlock closes the (serialized and non-preemptible) write side
+ * critical section of given seqlock_t.
+ */
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	write_seqcount_t_end(&sl-&