Merge tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Info Molnar:
 "Futex improvements:

   - Add the 'futex2' syscall ABI, which is an attempt to get away from
     the multiplex syscall and adds a little room for extentions, while
     lifting some limitations.

   - Fix futex PI recursive rt_mutex waiter state bug

   - Fix inter-process shared futexes on no-MMU systems

   - Use folios instead of pages

  Micro-optimizations of locking primitives:

   - Improve arch_spin_value_unlocked() on asm-generic ticket spinlock
     architectures, to improve lockref code generation

   - Improve the x86-32 lockref_get_not_zero() main loop by adding
     build-time CMPXCHG8B support detection for the relevant lockref
     code, and by better interfacing the CMPXCHG8B assembly code with
     the compiler

   - Introduce arch_sync_try_cmpxchg() on x86 to improve
     sync_try_cmpxchg() code generation. Convert some sync_cmpxchg()
     users to sync_try_cmpxchg().

   - Micro-optimize rcuref_put_slowpath()

  Locking debuggability improvements:

   - Improve CONFIG_DEBUG_RT_MUTEXES=y to have a fast-path as well

   - Enforce atomicity of sched_submit_work(), which is de-facto atomic
     but was un-enforced previously.

   - Extend <linux/cleanup.h>'s no_free_ptr() with __must_check
     semantics

   - Fix ww_mutex self-tests

   - Clean up const-propagation in <linux/seqlock.h> and simplify the
     API-instantiation macros a bit

  RT locking improvements:

   - Provide the rt_mutex_*_schedule() primitives/helpers and use them
     in the rtmutex code to avoid recursion vs. rtlock on the PI state.

   - Add nested blocking lockdep asserts to rt_mutex_lock(),
     rtlock_lock() and rwbase_read_lock()

  .. plus misc fixes & cleanups"

* tag 'locking-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  futex: Don't include process MM in futex key on no-MMU
  locking/seqlock: Fix grammar in comment
  alpha: Fix up new futex syscall numbers
  locking/seqlock: Propagate 'const' pointers within read-only methods, remove forced type casts
  locking/lockdep: Fix string sizing bug that triggers a format-truncation compiler-warning
  locking/seqlock: Change __seqprop() to return the function pointer
  locking/seqlock: Simplify SEQCOUNT_LOCKNAME()
  locking/atomics: Use atomic_try_cmpxchg_release() to micro-optimize rcuref_put_slowpath()
  locking/atomic, xen: Use sync_try_cmpxchg() instead of sync_cmpxchg()
  locking/atomic/x86: Introduce arch_sync_try_cmpxchg()
  locking/atomic: Add generic support for sync_try_cmpxchg() and its fallback
  locking/seqlock: Fix typo in comment
  futex/requeue: Remove unnecessary ‘NULL’ initialization from futex_proxy_trylock_atomic()
  locking/local, arch: Rewrite local_add_unless() as a static inline function
  locking/debug: Fix debugfs API return value checks to use IS_ERR()
  locking/ww_mutex/test: Make sure we bail out instead of livelock
  locking/ww_mutex/test: Fix potential workqueue corruption
  locking/ww_mutex/test: Use prng instead of rng to avoid hangs at bootup
  futex: Add sys_futex_requeue()
  futex: Add flags2 argument to futex_requeue()
  ...

1 files changed, 31 insertions, 21 deletions

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e9bd2f65d7f4..e92f9d5577ba 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -191,11 +191,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
  * @locktype:		LOCKNAME canonical C data type
  * @preemptible:	preemptibility of above locktype
- * @lockmember:		argument for lockdep_assert_held()
- * @lockbase:		associated lock release function (prefix only)
- * @lock_acquire:	associated lock acquisition function (full call)
+ * @lockbase:		prefix for associated lock/unlock
  */
-#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase)	\
 typedef struct seqcount_##lockname {					\
 	seqcount_t		seqcount;				\
 	__SEQ_LOCK(locktype	*lock);					\
@@ -207,6 +205,12 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 	return &s->seqcount;						\
 }									\
 									\
+static __always_inline const seqcount_t *				\
+__seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s)	\
+{									\
+	return &s->seqcount;						\
+}									\
+									\
 static __always_inline unsigned						\
 __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
 {									\
@@ -216,7 +220,7 @@ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
 		return seq;						\
 									\
 	if (preemptible && unlikely(seq & 1)) {				\
-		__SEQ_LOCK(lock_acquire);				\
+		__SEQ_LOCK(lockbase##_lock(s->lock));			\
 		__SEQ_LOCK(lockbase##_unlock(s->lock));			\
 									\
 		/*							\
@@ -242,7 +246,7 @@ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 static __always_inline void						\
 __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s)		\
 {									\
-	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
+	__SEQ_LOCK(lockdep_assert_held(s->lock));			\
 }
 
 /*
@@ -254,6 +258,11 @@ static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
 	return s;
 }
 
+static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s)
+{
+	return s;
+}
+
 static inline unsigned __seqprop_sequence(const seqcount_t *s)
 {
 	return READ_ONCE(s->sequence);
@@ -271,10 +280,10 @@ static inline void __seqprop_assert(const seqcount_t *s)
 
 #define __SEQ_RT	IS_ENABLED(CONFIG_PREEMPT_RT)
 
-SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    s->lock,        raw_spin, raw_spin_lock(s->lock))
-SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, s->lock,        spin,     spin_lock(s->lock))
-SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, s->lock,        read,     read_lock(s->lock))
-SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex,    mutex_lock(s->lock))
+SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    raw_spin)
+SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, spin)
+SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, read)
+SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
@@ -294,19 +303,20 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex
 #define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 
 #define __seqprop_case(s, lockname, prop)				\
-	seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s))
+	seqcount_##lockname##_t: __seqprop_##lockname##_##prop
 
 #define __seqprop(s, prop) _Generic(*(s),				\
-	seqcount_t:		__seqprop_##prop((void *)(s)),		\
+	seqcount_t:		__seqprop_##prop,			\
 	__seqprop_case((s),	raw_spinlock,	prop),			\
 	__seqprop_case((s),	spinlock,	prop),			\
 	__seqprop_case((s),	rwlock,		prop),			\
 	__seqprop_case((s),	mutex,		prop))
 
-#define seqprop_ptr(s)			__seqprop(s, ptr)
-#define seqprop_sequence(s)		__seqprop(s, sequence)
-#define seqprop_preemptible(s)		__seqprop(s, preemptible)
-#define seqprop_assert(s)		__seqprop(s, assert)
+#define seqprop_ptr(s)			__seqprop(s, ptr)(s)
+#define seqprop_const_ptr(s)		__seqprop(s, const_ptr)(s)
+#define seqprop_sequence(s)		__seqprop(s, sequence)(s)
+#define seqprop_preemptible(s)		__seqprop(s, preemptible)(s)
+#define seqprop_assert(s)		__seqprop(s, assert)(s)
 
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
@@ -355,7 +365,7 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex
  */
 #define read_seqcount_begin(s)						\
 ({									\
-	seqcount_lockdep_reader_access(seqprop_ptr(s));			\
+	seqcount_lockdep_reader_access(seqprop_const_ptr(s));		\
 	raw_read_seqcount_begin(s);					\
 })
 
@@ -421,7 +431,7 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex
  * Return: true if a read section retry is required, else false
  */
 #define __read_seqcount_retry(s, start)					\
-	do___read_seqcount_retry(seqprop_ptr(s), start)
+	do___read_seqcount_retry(seqprop_const_ptr(s), start)
 
 static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
@@ -441,7 +451,7 @@ static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start)
  * Return: true if a read section retry is required, else false
  */
 #define read_seqcount_retry(s, start)					\
-	do_read_seqcount_retry(seqprop_ptr(s), start)
+	do_read_seqcount_retry(seqprop_const_ptr(s), start)
 
 static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
@@ -574,7 +584,7 @@ static inline void do_write_seqcount_end(seqcount_t *s)
  * 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
+ * neither writes before nor after the barrier are enclosed in a seq-writer
  * critical section that would ensure readers are aware of ongoing writes::
  *
  *	seqcount_t seq;
@@ -864,7 +874,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 }
 
 /*
- * For all seqlock_t write side functions, use the the internal
+ * For all seqlock_t write side functions, use the internal
  * do_write_seqcount_begin() instead of generic write_seqcount_begin().
  * This way, no redundant lockdep_assert_held() checks are added.
  */