Merge tag 'locking-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Thomas Gleixner:
 "A moderate set of locking updates:

   - A few extensions to the rwsem API and support for opportunistic
     spinning and lock stealing

   - lockdep selftest improvements

   - Documentation updates

   - Cleanups and small fixes all over the place"

* tag 'locking-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  seqlock: kernel-doc: Specify when preemption is automatically altered
  seqlock: Prefix internal seqcount_t-only macros with a "do_"
  Documentation: seqlock: s/LOCKTYPE/LOCKNAME/g
  locking/rwsem: Remove reader optimistic spinning
  locking/rwsem: Enable reader optimistic lock stealing
  locking/rwsem: Prevent potential lock starvation
  locking/rwsem: Pass the current atomic count to rwsem_down_read_slowpath()
  locking/rwsem: Fold __down_{read,write}*()
  locking/rwsem: Introduce rwsem_write_trylock()
  locking/rwsem: Better collate rwsem_read_trylock()
  rwsem: Implement down_read_interruptible
  rwsem: Implement down_read_killable_nested
  refcount: Fix a kernel-doc markup
  completion: Drop init_completion define
  atomic: Update MAINTAINERS
  atomic: Delete obsolete documentation
  seqlock: Rename __seqprop() users
  lockdep/selftest: Add spin_nest_lock test
  lockdep/selftests: Fix PROVE_RAW_LOCK_NESTING
  seqlock: avoid -Wshadow warnings
  ...

Documentation/locking/seqlock.rst

@@ -89,7 +89,7 @@ Read path::
 
 .. _seqcount_locktype_t:
 
-Sequence counters with associated locks (``seqcount_LOCKTYPE_t``)
+Sequence counters with associated locks (``seqcount_LOCKNAME_t``)
 -----------------------------------------------------------------
 
 As discussed at :ref:`seqcount_t`, sequence count write side critical
@@ -115,27 +115,26 @@ The following sequence counters with associated locks are defined:
   - ``seqcount_mutex_t``
   - ``seqcount_ww_mutex_t``
 
-The plain seqcount read and write APIs branch out to the specific
-seqcount_LOCKTYPE_t implementation at compile-time. This avoids kernel
-API explosion per each new seqcount LOCKTYPE.
+The sequence counter read and write APIs can take either a plain
+seqcount_t or any of the seqcount_LOCKNAME_t variants above.
 
-Initialization (replace "LOCKTYPE" with one of the supported locks)::
+Initialization (replace "LOCKNAME" with one of the supported locks)::
 
 	/* dynamic */
-	seqcount_LOCKTYPE_t foo_seqcount;
-	seqcount_LOCKTYPE_init(&foo_seqcount, &lock);
+	seqcount_LOCKNAME_t foo_seqcount;
+	seqcount_LOCKNAME_init(&foo_seqcount, &lock);
 
 	/* static */
-	static seqcount_LOCKTYPE_t foo_seqcount =
-		SEQCNT_LOCKTYPE_ZERO(foo_seqcount, &lock);
+	static seqcount_LOCKNAME_t foo_seqcount =
+		SEQCNT_LOCKNAME_ZERO(foo_seqcount, &lock);
 
 	/* C99 struct init */
 	struct {
-		.seq   = SEQCNT_LOCKTYPE_ZERO(foo.seq, &lock),
+		.seq   = SEQCNT_LOCKNAME_ZERO(foo.seq, &lock),
 	} foo;
 
 Write path: same as in :ref:`seqcount_t`, while running from a context
-with the associated LOCKTYPE lock acquired.
+with the associated write serialization lock acquired.
 
 Read path: same as in :ref:`seqcount_t`.
 

MAINTAINERS

@@ -2982,6 +2982,8 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	arch/*/include/asm/atomic*.h
 F:	include/*/atomic*.h
+F:	include/linux/refcount.h
+F:	Documentation/atomic_*.txt
 F:	scripts/atomic/
 
 ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER

include/linux/completion.h

@@ -28,8 +28,7 @@ struct completion {
 	struct swait_queue_head wait;
 };
 
-#define init_completion_map(x, m) __init_completion(x)
-#define init_completion(x) __init_completion(x)
+#define init_completion_map(x, m) init_completion(x)
 static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 
@@ -82,7 +81,7 @@ static inline void complete_release(struct completion *x) {}
  * This inline function will initialize a dynamically created completion
  * structure.
  */
-static inline void __init_completion(struct completion *x)
+static inline void init_completion(struct completion *x)
 {
 	x->done = 0;
 	init_swait_queue_head(&x->wait);

include/linux/refcount.h

@@ -101,7 +101,7 @@
 struct mutex;
 
 /**
- * struct refcount_t - variant of atomic_t specialized for reference counts
+ * typedef refcount_t - variant of atomic_t specialized for reference counts
  * @refs: atomic_t counter field
  *
  * The counter saturates at REFCOUNT_SATURATED and will not move once

include/linux/rwsem.h

@@ -123,6 +123,7 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
  * lock for reading
  */
 extern void down_read(struct rw_semaphore *sem);
+extern int __must_check down_read_interruptible(struct rw_semaphore *sem);
 extern int __must_check down_read_killable(struct rw_semaphore *sem);
 
 /*
@@ -171,6 +172,7 @@ extern void downgrade_write(struct rw_semaphore *sem);
  * See Documentation/locking/lockdep-design.rst for more details.)
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
+extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
 extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass);
 extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock);
@@ -191,6 +193,7 @@ extern void down_read_non_owner(struct rw_semaphore *sem);
 extern void up_read_non_owner(struct rw_semaphore *sem);
 #else
 # define down_read_nested(sem, subclass)		down_read(sem)
+# define down_read_killable_nested(sem, subclass)	down_read_killable(sem)
 # define down_write_nest_lock(sem, nest_lock)	down_write(sem)
 # define down_write_nested(sem, subclass)	down_write(sem)
 # define down_write_killable_nested(sem, subclass)	down_write_killable(sem)

kernel/futex.c

@@ -310,8 +310,6 @@ static inline bool should_fail_futex(bool fshared)
 
 #ifdef CONFIG_COMPAT
 static void compat_exit_robust_list(struct task_struct *curr);
-#else
-static inline void compat_exit_robust_list(struct task_struct *curr) { }
 #endif
 
 /*

kernel/locking/lock_events_list.h

@@ -56,13 +56,11 @@ LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
 LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
 LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
 LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
-LOCK_EVENT(rwsem_opt_rlock)	/* # of opt-acquired read locks		*/
-LOCK_EVENT(rwsem_opt_wlock)	/* # of opt-acquired write locks	*/
+LOCK_EVENT(rwsem_opt_lock)	/* # of opt-acquired write locks	*/
 LOCK_EVENT(rwsem_opt_fail)	/* # of failed optspins			*/
 LOCK_EVENT(rwsem_opt_nospin)	/* # of disabled optspins		*/
-LOCK_EVENT(rwsem_opt_norspin)	/* # of disabled reader-only optspins	*/
-LOCK_EVENT(rwsem_opt_rlock2)	/* # of opt-acquired 2ndary read locks	*/
 LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
+LOCK_EVENT(rwsem_rlock_steal)	/* # of read locks by lock stealing	*/
 LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
 LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
 LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/

lib/locking-selftest.c

@@ -58,10 +58,10 @@ static struct ww_mutex o, o2, o3;
  * Normal standalone locks, for the circular and irq-context
  * dependency tests:
  */
-static DEFINE_RAW_SPINLOCK(lock_A);
-static DEFINE_RAW_SPINLOCK(lock_B);
-static DEFINE_RAW_SPINLOCK(lock_C);
-static DEFINE_RAW_SPINLOCK(lock_D);
+static DEFINE_SPINLOCK(lock_A);
+static DEFINE_SPINLOCK(lock_B);
+static DEFINE_SPINLOCK(lock_C);
+static DEFINE_SPINLOCK(lock_D);
 
 static DEFINE_RWLOCK(rwlock_A);
 static DEFINE_RWLOCK(rwlock_B);
@@ -93,12 +93,12 @@ static DEFINE_RT_MUTEX(rtmutex_D);
  * but X* and Y* are different classes. We do this so that
  * we do not trigger a real lockup:
  */
-static DEFINE_RAW_SPINLOCK(lock_X1);
-static DEFINE_RAW_SPINLOCK(lock_X2);
-static DEFINE_RAW_SPINLOCK(lock_Y1);
-static DEFINE_RAW_SPINLOCK(lock_Y2);
-static DEFINE_RAW_SPINLOCK(lock_Z1);
-static DEFINE_RAW_SPINLOCK(lock_Z2);
+static DEFINE_SPINLOCK(lock_X1);
+static DEFINE_SPINLOCK(lock_X2);
+static DEFINE_SPINLOCK(lock_Y1);
+static DEFINE_SPINLOCK(lock_Y2);
+static DEFINE_SPINLOCK(lock_Z1);
+static DEFINE_SPINLOCK(lock_Z2);
 
 static DEFINE_RWLOCK(rwlock_X1);
 static DEFINE_RWLOCK(rwlock_X2);
@@ -138,10 +138,10 @@ static DEFINE_RT_MUTEX(rtmutex_Z2);
  */
 #define INIT_CLASS_FUNC(class) 				\
 static noinline void					\
-init_class_##class(raw_spinlock_t *lock, rwlock_t *rwlock, \
+init_class_##class(spinlock_t *lock, rwlock_t *rwlock, \
 	struct mutex *mutex, struct rw_semaphore *rwsem)\
 {							\
-	raw_spin_lock_init(lock);			\
+	spin_lock_init(lock);			\
 	rwlock_init(rwlock);				\
 	mutex_init(mutex);				\
 	init_rwsem(rwsem);				\
@@ -210,10 +210,10 @@ static void init_shared_classes(void)
  * Shortcuts for lock/unlock API variants, to keep
  * the testcases compact:
  */
-#define L(x)			raw_spin_lock(&lock_##x)
-#define U(x)			raw_spin_unlock(&lock_##x)
+#define L(x)			spin_lock(&lock_##x)
+#define U(x)			spin_unlock(&lock_##x)
 #define LU(x)			L(x); U(x)
-#define SI(x)			raw_spin_lock_init(&lock_##x)
+#define SI(x)			spin_lock_init(&lock_##x)
 
 #define WL(x)			write_lock(&rwlock_##x)
 #define WU(x)			write_unlock(&rwlock_##x)
@@ -1341,7 +1341,7 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion3_soft_wlock)
 
 #define I2(x)					\
 	do {					\
-		raw_spin_lock_init(&lock_##x);	\
+		spin_lock_init(&lock_##x);	\
 		rwlock_init(&rwlock_##x);	\
 		mutex_init(&mutex_##x);		\
 		init_rwsem(&rwsem_##x);		\
@@ -2005,10 +2005,23 @@ static void ww_test_edeadlk_acquire_wrong_slow(void)
 
 static void ww_test_spin_nest_unlocked(void)
 {
-	raw_spin_lock_nest_lock(&lock_A, &o.base);
+	spin_lock_nest_lock(&lock_A, &o.base);
 	U(A);
 }
 
+/* This is not a deadlock, because we have X1 to serialize Y1 and Y2 */
+static void ww_test_spin_nest_lock(void)
+{
+	spin_lock(&lock_X1);
+	spin_lock_nest_lock(&lock_Y1, &lock_X1);
+	spin_lock(&lock_A);
+	spin_lock_nest_lock(&lock_Y2, &lock_X1);
+	spin_unlock(&lock_A);
+	spin_unlock(&lock_Y2);
+	spin_unlock(&lock_Y1);
+	spin_unlock(&lock_X1);
+}
+
 static void ww_test_unneeded_slow(void)
 {
 	WWAI(&t);
@@ -2226,6 +2239,10 @@ static void ww_tests(void)
 	dotest(ww_test_spin_nest_unlocked, FAILURE, LOCKTYPE_WW);
 	pr_cont("\n");
 
+	print_testname("spinlock nest test");
+	dotest(ww_test_spin_nest_lock, SUCCESS, LOCKTYPE_WW);
+	pr_cont("\n");
+
 	printk("  -----------------------------------------------------\n");
 	printk("                                 |block | try  |context|\n");
 	printk("  -----------------------------------------------------\n");