locking: Move the rwsem code to kernel/locking/

Notably: changed lib/rwsem* targets from lib- to obj-, no idea about
the ramifications of that.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-g0kynfh5feriwc6p3h6kpbw6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/Makefile

@@ -8,7 +8,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o task_work.o \
 	    extable.o params.o posix-timers.o \
 	    kthread.o sys_ni.o posix-cpu-timers.o \
-	    hrtimer.o rwsem.o nsproxy.o \
+	    hrtimer.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o groups.o lglock.o smpboot.o
 

kernel/locking/Makefile

@@ -1,5 +1,5 @@
 
-obj-y += mutex.o semaphore.o
+obj-y += mutex.o semaphore.o rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -20,3 +20,5 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o

kernel/locking/rwsem-spinlock.c

@@ -0,0 +1,296 @@
+/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
+ * generic spinlock implementation
+ *
+ * Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ * - Derived also from comments by Linus
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+};
+
+int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	int ret = 1;
+	unsigned long flags;
+
+	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
+		ret = (sem->activity != 0);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rwsem_is_locked);
+
+/*
+ * initialise the semaphore
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->activity = 0;
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+EXPORT_SYMBOL(__init_rwsem);
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here, then:
+ *   - the 'active count' _reached_ zero
+ *   - the 'waiting count' is non-zero
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if wakewrite is non-zero
+ */
+static inline struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	int woken;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wakewrite)
+			/* Wake up a writer. Note that we do not grant it the
+			 * lock - it will have to acquire it when it runs. */
+			wake_up_process(waiter->task);
+		goto out;
+	}
+
+	/* grant an infinite number of read locks to the front of the queue */
+	woken = 0;
+	do {
+		struct list_head *next = waiter->list.next;
+
+		list_del(&waiter->list);
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+		woken++;
+		if (next == &sem->wait_list)
+			break;
+		waiter = list_entry(next, struct rwsem_waiter, list);
+	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+	sem->activity += woken;
+
+ out:
+	return sem;
+}
+
+/*
+ * wake a single writer
+ */
+static inline struct rw_semaphore *
+__rwsem_wake_one_writer(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter *waiter;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	wake_up_process(waiter->task);
+
+	return sem;
+}
+
+/*
+ * get a read lock on the semaphore
+ */
+void __sched __down_read(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+		goto out;
+	}
+
+	tsk = current;
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	get_task_struct(tsk);
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we don't need to touch the semaphore struct anymore */
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	/* wait to be given the lock */
+	for (;;) {
+		if (!waiter.task)
+			break;
+		schedule();
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	}
+
+	tsk->state = TASK_RUNNING;
+ out:
+	;
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		ret = 1;
+	}
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * get a write lock on the semaphore
+ */
+void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* set up my own style of waitqueue */
+	tsk = current;
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* wait for someone to release the lock */
+	for (;;) {
+		/*
+		 * That is the key to support write lock stealing: allows the
+		 * task already on CPU to get the lock soon rather than put
+		 * itself into sleep and waiting for system woke it or someone
+		 * else in the head of the wait list up.
+		 */
+		if (sem->activity == 0)
+			break;
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+		schedule();
+		raw_spin_lock_irqsave(&sem->wait_lock, flags);
+	}
+	/* got the lock */
+	sem->activity = -1;
+	list_del(&waiter.list);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+void __sched __down_write(struct rw_semaphore *sem)
+{
+	__down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+int __down_write_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity == 0) {
+		/* got the lock */
+		sem->activity = -1;
+		ret = 1;
+	}
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * release a read lock on the semaphore
+ */
+void __up_read(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+		sem = __rwsem_wake_one_writer(sem);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * release a write lock on the semaphore
+ */
+void __up_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	sem->activity = 0;
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 1);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - just wake up any readers at the front of the queue
+ */
+void __downgrade_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	sem->activity = 1;
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 0);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+}
+

kernel/locking/rwsem-xadd.c

@@ -0,0 +1,293 @@
+/* rwsem.c: R/W semaphores: contention handling functions
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ * Derived from arch/i386/kernel/semaphore.c
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
+ * and Michel Lespinasse <walken@google.com>
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/export.h>
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->count = RWSEM_UNLOCKED_VALUE;
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+
+EXPORT_SYMBOL(__init_rwsem);
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+};
+
+enum rwsem_wake_type {
+	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
+	RWSEM_WAKE_READERS,	/* Wake readers only */
+	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
+};
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then:
+ *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
+ *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
+ * - there must be someone on the queue
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if downgrading is false
+ */
+static struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	struct list_head *next;
+	long oldcount, woken, loop, adjustment;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wake_type == RWSEM_WAKE_ANY)
+			/* Wake writer at the front of the queue, but do not
+			 * grant it the lock yet as we want other writers
+			 * to be able to steal it.  Readers, on the other hand,
+			 * will block as they will notice the queued writer.
+			 */
+			wake_up_process(waiter->task);
+		goto out;
+	}
+
+	/* Writers might steal the lock before we grant it to the next reader.
+	 * We prefer to do the first reader grant before counting readers
+	 * so we can bail out early if a writer stole the lock.
+	 */
+	adjustment = 0;
+	if (wake_type != RWSEM_WAKE_READ_OWNED) {
+		adjustment = RWSEM_ACTIVE_READ_BIAS;
+ try_reader_grant:
+		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
+			/* A writer stole the lock. Undo our reader grant. */
+			if (rwsem_atomic_update(-adjustment, sem) &
+						RWSEM_ACTIVE_MASK)
+				goto out;
+			/* Last active locker left. Retry waking readers. */
+			goto try_reader_grant;
+		}
+	}
+
+	/* Grant an infinite number of read locks to the readers at the front
+	 * of the queue.  Note we increment the 'active part' of the count by
+	 * the number of readers before waking any processes up.
+	 */
+	woken = 0;
+	do {
+		woken++;
+
+		if (waiter->list.next == &sem->wait_list)
+			break;
+
+		waiter = list_entry(waiter->list.next,
+					struct rwsem_waiter, list);
+
+	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
+
+	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	if (waiter->type != RWSEM_WAITING_FOR_WRITE)
+		/* hit end of list above */
+		adjustment -= RWSEM_WAITING_BIAS;
+
+	if (adjustment)
+		rwsem_atomic_add(adjustment, sem);
+
+	next = sem->wait_list.next;
+	loop = woken;
+	do {
+		waiter = list_entry(next, struct rwsem_waiter, list);
+		next = waiter->list.next;
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+	} while (--loop);
+
+	sem->wait_list.next = next;
+	next->prev = &sem->wait_list;
+
+ out:
+	return sem;
+}
+
+/*
+ * wait for the read lock to be granted
+ */
+struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk = current;
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	get_task_struct(tsk);
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list))
+		adjustment += RWSEM_WAITING_BIAS;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = rwsem_atomic_update(adjustment, sem);
+
+	/* If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (count == RWSEM_WAITING_BIAS ||
+	    (count > RWSEM_WAITING_BIAS &&
+	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		if (!waiter.task)
+			break;
+		schedule();
+	}
+
+	tsk->state = TASK_RUNNING;
+
+	return sem;
+}
+
+/*
+ * wait until we successfully acquire the write lock
+ */
+struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+	long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk = current;
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list))
+		adjustment += RWSEM_WAITING_BIAS;
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = rwsem_atomic_update(adjustment, sem);
+
+	/* If there were already threads queued before us and there are no
+	 * active writers, the lock must be read owned; so we try to wake
+	 * any read locks that were queued ahead of us. */
+	if (count > RWSEM_WAITING_BIAS &&
+	    adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+
+	/* wait until we successfully acquire the lock */
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	while (true) {
+		if (!(count & RWSEM_ACTIVE_MASK)) {
+			/* Try acquiring the write lock. */
+			count = RWSEM_ACTIVE_WRITE_BIAS;
+			if (!list_is_singular(&sem->wait_list))
+				count += RWSEM_WAITING_BIAS;
+
+			if (sem->count == RWSEM_WAITING_BIAS &&
+			    cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) ==
+							RWSEM_WAITING_BIAS)
+				break;
+		}
+
+		raw_spin_unlock_irq(&sem->wait_lock);
+
+		/* Block until there are no active lockers. */
+		do {
+			schedule();
+			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+
+		raw_spin_lock_irq(&sem->wait_lock);
+	}
+
+	list_del(&waiter.list);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	tsk->state = TASK_RUNNING;
+
+	return sem;
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+EXPORT_SYMBOL(rwsem_down_read_failed);
+EXPORT_SYMBOL(rwsem_down_write_failed);
+EXPORT_SYMBOL(rwsem_wake);
+EXPORT_SYMBOL(rwsem_downgrade_wake);