Merge tag 'locking-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - rwsem micro-optimizations

 - spinlock micro-optimizations

 - cleanups, simplifications

* tag 'locking-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  vduse: Remove include of rwlock.h
  locking/lockdep: Remove lockdep_init_map_crosslock.
  x86/ACPI/boot: Use try_cmpxchg() in __acpi_{acquire,release}_global_lock()
  x86/PAT: Use try_cmpxchg() in set_page_memtype()
  locking/rwsem: Disable preemption in all down_write*() and up_write() code paths
  locking/rwsem: Disable preemption in all down_read*() and up_read() code paths
  locking/rwsem: Prevent non-first waiter from spinning in down_write() slowpath
  locking/qspinlock: Micro-optimize pending state waiting for unlock

Author: torvalds

arch/x86/kernel/acpi/boot.c

@@ -1840,23 +1840,23 @@ early_param("acpi_sci", setup_acpi_sci);
 
 int __acpi_acquire_global_lock(unsigned int *lock)
 {
-	unsigned int old, new, val;
+	unsigned int old, new;
+
+	old = READ_ONCE(*lock);
 	do {
-		old = *lock;
 		new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1));
-		val = cmpxchg(lock, old, new);
-	} while (unlikely (val != old));
+	} while (!try_cmpxchg(lock, &old, new));
 	return ((new & 0x3) < 3) ? -1 : 0;
 }
 
 int __acpi_release_global_lock(unsigned int *lock)
 {
-	unsigned int old, new, val;
+	unsigned int old, new;
+
+	old = READ_ONCE(*lock);
 	do {
-		old = *lock;
 		new = old & ~0x3;
-		val = cmpxchg(lock, old, new);
-	} while (unlikely (val != old));
+	} while (!try_cmpxchg(lock, &old, new));
 	return old & 0x1;
 }
 

arch/x86/mm/pat/memtype.c

@@ -159,10 +159,10 @@ static inline void set_page_memtype(struct page *pg,
 		break;
 	}
 
+	old_flags = READ_ONCE(pg->flags);
 	do {
-		old_flags = pg->flags;
 		new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
-	} while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
+	} while (!try_cmpxchg(&pg->flags, &old_flags, new_flags));
 }
 #else
 static inline enum page_cache_mode get_page_memtype(struct page *pg)

drivers/vdpa/vdpa_user/iova_domain.h

@@ -14,7 +14,6 @@
 #include <linux/iova.h>
 #include <linux/dma-mapping.h>
 #include <linux/vhost_iotlb.h>
-#include <linux/rwlock.h>
 
 #define IOVA_START_PFN 1
 

include/linux/lockdep.h

@@ -435,7 +435,6 @@ enum xhlock_context_t {
 	XHLOCK_CTX_NR,
 };
 
-#define lockdep_init_map_crosslock(m, n, k, s) do {} while (0)
 /*
  * To initialize a lockdep_map statically use this macro.
  * Note that _name must not be NULL.

kernel/locking/qspinlock.c

@@ -371,7 +371,7 @@ void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	/*
 	 * We're pending, wait for the owner to go away.
 	 *
-	 * 0,1,1 -> 0,1,0
+	 * 0,1,1 -> *,1,0
 	 *
 	 * this wait loop must be a load-acquire such that we match the
 	 * store-release that clears the locked bit and create lock
@@ -380,7 +380,7 @@ void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * barriers.
 	 */
 	if (val & _Q_LOCKED_MASK)
-		atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK));
+		smp_cond_load_acquire(&lock->locked, !VAL);
 
 	/*
 	 * take ownership and clear the pending bit.

kernel/locking/rwsem.c

@@ -256,16 +256,13 @@ static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp)
 static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp = RWSEM_UNLOCKED_VALUE;
-	bool ret = false;
 
-	preempt_disable();
 	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
 		rwsem_set_owner(sem);
-		ret = true;
+		return true;
 	}
 
-	preempt_enable();
-	return ret;
+	return false;
 }
 
 /*
@@ -624,18 +621,16 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 			 */
 			if (first->handoff_set && (waiter != first))
 				return false;
-
-			/*
-			 * First waiter can inherit a previously set handoff
-			 * bit and spin on rwsem if lock acquisition fails.
-			 */
-			if (waiter == first)
-				waiter->handoff_set = true;
 		}
 
 		new = count;
 
 		if (count & RWSEM_LOCK_MASK) {
+			/*
+			 * A waiter (first or not) can set the handoff bit
+			 * if it is an RT task or wait in the wait queue
+			 * for too long.
+			 */
 			if (has_handoff || (!rt_task(waiter->task) &&
 					    !time_after(jiffies, waiter->timeout)))
 				return false;
@@ -651,11 +646,12 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));
 
 	/*
-	 * We have either acquired the lock with handoff bit cleared or
-	 * set the handoff bit.
+	 * We have either acquired the lock with handoff bit cleared or set
+	 * the handoff bit. Only the first waiter can have its handoff_set
+	 * set here to enable optimistic spinning in slowpath loop.
 	 */
 	if (new & RWSEM_FLAG_HANDOFF) {
-		waiter->handoff_set = true;
+		first->handoff_set = true;
 		lockevent_inc(rwsem_wlock_handoff);
 		return false;
 	}
@@ -717,7 +713,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		return false;
 	}
 
-	preempt_disable();
 	/*
 	 * Disable preemption is equal to the RCU read-side crital section,
 	 * thus the task_strcut structure won't go away.
@@ -729,7 +724,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	if ((flags & RWSEM_NONSPINNABLE) ||
 	    (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner)))
 		ret = false;
-	preempt_enable();
 
 	lockevent_cond_inc(rwsem_opt_fail, !ret);
 	return ret;
@@ -829,8 +823,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	int loop = 0;
 	u64 rspin_threshold = 0;
 
-	preempt_disable();
-
 	/* sem->wait_lock should not be held when doing optimistic spinning */
 	if (!osq_lock(&sem->osq))
 		goto done;
@@ -938,7 +930,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	}
 	osq_unlock(&sem->osq);
 done:
-	preempt_enable();
 	lockevent_cond_inc(rwsem_opt_fail, !taken);
 	return taken;
 }
@@ -1092,7 +1083,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 			/* Ordered by sem->wait_lock against rwsem_mark_wake(). */
 			break;
 		}
-		schedule();
+		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_reader);
 	}
 
@@ -1179,15 +1170,12 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 		if (waiter.handoff_set) {
 			enum owner_state owner_state;
 
-			preempt_disable();
 			owner_state = rwsem_spin_on_owner(sem);
-			preempt_enable();
-
 			if (owner_state == OWNER_NULL)
 				goto trylock_again;
 		}
 
-		schedule();
+		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_writer);
 		set_current_state(state);
 trylock_again:
@@ -1254,14 +1242,20 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
  */
 static inline int __down_read_common(struct rw_semaphore *sem, int state)
 {
+	int ret = 0;
 	long count;
 
+	preempt_disable();
 	if (!rwsem_read_trylock(sem, &count)) {
-		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state)))
-			return -EINTR;
+		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state))) {
+			ret = -EINTR;
+			goto out;
+		}
 		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	}
-	return 0;
+out:
+	preempt_enable();
+	return ret;
 }
 
 static inline void __down_read(struct rw_semaphore *sem)
@@ -1281,32 +1275,39 @@ static inline int __down_read_killable(struct rw_semaphore *sem)
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
+	int ret = 0;
 	long tmp;
 
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 
+	preempt_disable();
 	tmp = atomic_long_read(&sem->count);
 	while (!(tmp & RWSEM_READ_FAILED_MASK)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
 						    tmp + RWSEM_READER_BIAS)) {
 			rwsem_set_reader_owned(sem);
-			return 1;
+			ret = 1;
+			break;
 		}
 	}
-	return 0;
+	preempt_enable();
+	return ret;
 }
 
 /*
  * lock for writing
  */
 static inline int __down_write_common(struct rw_semaphore *sem, int state)
 {
+	int ret = 0;
+
+	preempt_disable();
 	if (unlikely(!rwsem_write_trylock(sem))) {
 		if (IS_ERR(rwsem_down_write_slowpath(sem, state)))
-			return -EINTR;
+			ret = -EINTR;
 	}
-
-	return 0;
+	preempt_enable();
+	return ret;
 }
 
 static inline void __down_write(struct rw_semaphore *sem)
@@ -1321,8 +1322,14 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
 
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
+	int ret;
+
+	preempt_disable();
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
-	return rwsem_write_trylock(sem);
+	ret = rwsem_write_trylock(sem);
+	preempt_enable();
+
+	return ret;
 }
 
 /*
@@ -1335,6 +1342,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 
+	preempt_disable();
 	rwsem_clear_reader_owned(sem);
 	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
 	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
@@ -1343,6 +1351,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 		clear_nonspinnable(sem);
 		rwsem_wake(sem);
 	}
+	preempt_enable();
 }
 
 /*
@@ -1363,9 +1372,9 @@ static inline void __up_write(struct rw_semaphore *sem)
 	preempt_disable();
 	rwsem_clear_owner(sem);
 	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
-	preempt_enable();
 	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
 		rwsem_wake(sem);
+	preempt_enable();
 }
 
 /*
@@ -1383,11 +1392,13 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	 * write side. As such, rely on RELEASE semantics.
 	 */
 	DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem);
+	preempt_disable();
 	tmp = atomic_long_fetch_add_release(
 		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
 	rwsem_set_reader_owned(sem);
 	if (tmp & RWSEM_FLAG_WAITERS)
 		rwsem_downgrade_wake(sem);
+	preempt_enable();
 }
 
 #else /* !CONFIG_PREEMPT_RT */
@@ -1662,6 +1673,12 @@ void down_read_non_owner(struct rw_semaphore *sem)
 {
 	might_sleep();
 	__down_read(sem);
+	/*
+	 * The owner value for a reader-owned lock is mostly for debugging
+	 * purpose only and is not critical to the correct functioning of
+	 * rwsem. So it is perfectly fine to set it in a preempt-enabled
+	 * context here.
+	 */
 	__rwsem_set_reader_owned(sem, NULL);
 }
 EXPORT_SYMBOL(down_read_non_owner);