[PATCH v2 0/2] locking/rwsem: Convert rwsem count to atomic_long_t

[PATCH v2 0/2] locking/rwsem: Convert rwsem count to atomic_long_t

[Jason Low]

v1->v2:
- Also convert sem->count usages in arch/{alph,ia64}/include/asm/rwsem.h
  to be used as atomic_long_t.

- Merge the patches to remove rwsem_atomic_add() and rwsem_atomic_update()
  across the various architectures into one patch.

This series converts the rwsem count variable to an atomic_long_t
since it is used it as an atomic variable. This allows us to also remove
the rwsem_atomic_{add,update} abstraction and reduce 100+ lines of code.

Jason Low (2):
  locking/rwsem: Convert sem->count to atomic_long_t
  Remove rwsem_atomic_add() and rwsem_atomic_update()

 arch/alpha/include/asm/rwsem.h | 68 ++++++++----------------------------------
 arch/ia64/include/asm/rwsem.h  | 31 ++++++++-----------
 arch/s390/include/asm/rwsem.h  | 37 -----------------------
 arch/x86/include/asm/rwsem.h   | 18 -----------
 include/asm-generic/rwsem.h    | 22 ++------------
 include/linux/rwsem.h          |  6 ++--
 kernel/locking/rwsem-xadd.c    | 32 ++++++++++----------
 7 files changed, 48 insertions(+), 166 deletions(-)

-- 
2.1.4

[PATCH v2 1/2] locking/rwsem: Convert sem->count to atomic_long_t

[Jason Low]

Convert the rwsem count variable to an atomic_long_t since we use it
as an atomic variable. This also allows us to remove the
rwsem_atomic_{add,update} "abstraction" which would now be an unnecesary
level of indirection. In follow up patches, we also remove the
rwsem_atomic_{add,update} definitions across the various architectures.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jason Low <jason.low2@hpe.com>
---
 arch/alpha/include/asm/rwsem.h | 26 +++++++++++++-------------
 arch/ia64/include/asm/rwsem.h  | 24 ++++++++++++------------
 include/asm-generic/rwsem.h    |  6 +++---
 include/linux/rwsem.h          |  6 +++---
 kernel/locking/rwsem-xadd.c    | 32 +++++++++++++++++---------------
 5 files changed, 48 insertions(+), 46 deletions(-)

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 0131a70..b40021a 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -25,8 +25,8 @@ static inline void __down_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -52,13 +52,13 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long old, new, res;
 
-	res = sem->count;
+	res = atomic_long_read(&sem->count);
 	do {
 		new = res + RWSEM_ACTIVE_READ_BIAS;
 		if (new <= 0)
 			break;
 		old = res;
-		res = cmpxchg(&sem->count, old, new);
+		res = atomic_long_cmpxchg(&sem->count, old, new);
 	} while (res != old);
 	return res >= 0 ? 1 : 0;
 }
@@ -67,8 +67,8 @@ static inline long ___down_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_WRITE_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -106,7 +106,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+	long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 			   RWSEM_ACTIVE_WRITE_BIAS);
 	if (ret == RWSEM_UNLOCKED_VALUE)
 		return 1;
@@ -117,8 +117,8 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -142,8 +142,8 @@ static inline void __up_write(struct rw_semaphore *sem)
 {
 	long count;
 #ifndef	CONFIG_SMP
-	sem->count -= RWSEM_ACTIVE_WRITE_BIAS;
-	count = sem->count;
+	sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
+	count = sem->count.counter;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -171,8 +171,8 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_WAITING_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_WAITING_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 8b23e07..c5d544f 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -40,7 +40,7 @@
 static inline void
 __down_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count, 1);
+	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
 
 	if (result < 0)
 		rwsem_down_read_failed(sem);
@@ -55,9 +55,9 @@ ___down_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old + RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_acq(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
 
 	return old;
 }
@@ -85,7 +85,7 @@ __down_write_killable (struct rw_semaphore *sem)
 static inline void
 __up_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count, -1);
+	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
 
 	if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -100,9 +100,9 @@ __up_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -115,8 +115,8 @@ static inline int
 __down_read_trylock (struct rw_semaphore *sem)
 {
 	long tmp;
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acq(&sem->count, tmp, tmp+1)) {
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
 			return 1;
 		}
 	}
@@ -129,8 +129,8 @@ __down_read_trylock (struct rw_semaphore *sem)
 static inline int
 __down_write_trylock (struct rw_semaphore *sem)
 {
-	long tmp = cmpxchg_acq(&sem->count, RWSEM_UNLOCKED_VALUE,
-			      RWSEM_ACTIVE_WRITE_BIAS);
+	long tmp = atomic_long_cmpxchg_acquire(&sem->count,
+			RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
 
@@ -143,9 +143,9 @@ __downgrade_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_WAITING_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (old < 0)
 		rwsem_downgrade_wake(sem);
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index 3fc94a0..a3a93ec 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -41,8 +41,8 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acquire(&sem->count, tmp,
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
@@ -79,7 +79,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index d37fbb3..cb4d4aa 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -26,7 +26,7 @@ struct rw_semaphore;
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long count;
+	atomic_long_t count;
 	struct list_head wait_list;
 	raw_spinlock_t wait_lock;
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -54,7 +54,7 @@ extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return sem->count != 0;
+	return atomic_long_read(&sem->count) != 0;
 }
 
 #endif
@@ -74,7 +74,7 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
-	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	{ .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE),	\
 	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index b957da7..63b40a5 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -80,7 +80,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-	sem->count = RWSEM_UNLOCKED_VALUE;
+	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -153,10 +153,11 @@ __rwsem_mark_wake(struct rw_semaphore *sem,
 	if (wake_type != RWSEM_WAKE_READ_OWNED) {
 		adjustment = RWSEM_ACTIVE_READ_BIAS;
  try_reader_grant:
-		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+		oldcount = atomic_long_add_return(adjustment, &sem->count) - adjustment;
+
 		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
 			/* A writer stole the lock. Undo our reader grant. */
-			if (rwsem_atomic_update(-adjustment, sem) &
+			if (atomic_long_sub_return(adjustment, &sem->count) &
 						RWSEM_ACTIVE_MASK)
 				goto out;
 			/* Last active locker left. Retry waking readers. */
@@ -186,7 +187,7 @@ __rwsem_mark_wake(struct rw_semaphore *sem,
 		adjustment -= RWSEM_WAITING_BIAS;
 
 	if (adjustment)
-		rwsem_atomic_add(adjustment, sem);
+		atomic_long_add(adjustment, &sem->count);
 
 	next = sem->wait_list.next;
 	loop = woken;
@@ -233,7 +234,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	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);
+	count = atomic_long_add_return(adjustment, &sem->count);
 
 	/* If there are no active locks, wake the front queued process(es).
 	 *
@@ -282,7 +283,8 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 			RWSEM_ACTIVE_WRITE_BIAS :
 			RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
 
-	if (cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) {
+	if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count)
+							== RWSEM_WAITING_BIAS) {
 		rwsem_set_owner(sem);
 		return true;
 	}
@@ -296,13 +298,13 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = READ_ONCE(sem->count);
+	long old, count = atomic_long_read(&sem->count);
 
 	while (true) {
 		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
 			return false;
 
-		old = cmpxchg_acquire(&sem->count, count,
+		old = atomic_long_cmpxchg_acquire(&sem->count, count,
 				      count + RWSEM_ACTIVE_WRITE_BIAS);
 		if (old == count) {
 			rwsem_set_owner(sem);
@@ -324,7 +326,7 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
 	if (!owner) {
-		long count = READ_ONCE(sem->count);
+		long count = atomic_long_read(&sem->count);
 		/*
 		 * If sem->owner is not set, yet we have just recently entered the
 		 * slowpath with the lock being active, then there is a possibility
@@ -375,7 +377,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
 	 * held by readers. Check the counter to verify the
 	 * state.
 	 */
-	count = READ_ONCE(sem->count);
+	count = atomic_long_read(&sem->count);
 	return (count == 0 || count == RWSEM_WAITING_BIAS);
 }
 
@@ -460,7 +462,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	WAKE_Q(wake_q);
 
 	/* undo write bias from down_write operation, stop active locking */
-	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
+	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
 
 	/* do optimistic spinning and steal lock if possible */
 	if (rwsem_optimistic_spin(sem))
@@ -483,7 +485,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 	/* we're now waiting on the lock, but no longer actively locking */
 	if (waiting) {
-		count = READ_ONCE(sem->count);
+		count = atomic_long_read(&sem->count);
 
 		/*
 		 * If there were already threads queued before us and there are
@@ -505,7 +507,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 		}
 
 	} else
-		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+		count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count);
 
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
@@ -521,7 +523,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 			schedule();
 			set_current_state(state);
-		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
@@ -536,7 +538,7 @@ out_nolock:
 	raw_spin_lock_irq(&sem->wait_lock);
 	list_del(&waiter.list);
 	if (list_empty(&sem->wait_list))
-		rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
 	else
 		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
-- 
2.1.4

[tip:locking/core] locking/rwsem: Convert sem->count to 'atomic_long_t'

[tip-bot for Jason Low]

Commit-ID:  8ee62b1870be8e630158701632a533d0378e15b8
Gitweb:     http://git.kernel.org/tip/8ee62b1870be8e630158701632a533d0378e15b8
Author:     Jason Low <jason.low2@hpe.com>
AuthorDate: Fri, 3 Jun 2016 22:26:02 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 8 Jun 2016 15:16:42 +0200

locking/rwsem: Convert sem->count to 'atomic_long_t'

Convert the rwsem count variable to an atomic_long_t since we use it
as an atomic variable. This also allows us to remove the
rwsem_atomic_{add,update}() "abstraction" which would now be an unnecesary
level of indirection. In follow up patches, we also remove the
rwsem_atomic_{add,update}() definitions across the various architectures.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jason Low <jason.low2@hpe.com>
[ Build warning fixes on various architectures. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Terry Rudd <terry.rudd@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Waiman Long <Waiman.Long@hpe.com>
Link: http://lkml.kernel.org/r/1465017963-4839-2-git-send-email-jason.low2@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/rwsem.h | 26 +++++++++++++-------------
 arch/ia64/include/asm/rwsem.h  | 24 ++++++++++++------------
 include/asm-generic/rwsem.h    |  6 +++---
 include/linux/rwsem.h          |  8 +++++---
 kernel/locking/rwsem-xadd.c    | 32 +++++++++++++++++---------------
 5 files changed, 50 insertions(+), 46 deletions(-)

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index 0131a70..b40021a 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -25,8 +25,8 @@ static inline void __down_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -52,13 +52,13 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long old, new, res;
 
-	res = sem->count;
+	res = atomic_long_read(&sem->count);
 	do {
 		new = res + RWSEM_ACTIVE_READ_BIAS;
 		if (new <= 0)
 			break;
 		old = res;
-		res = cmpxchg(&sem->count, old, new);
+		res = atomic_long_cmpxchg(&sem->count, old, new);
 	} while (res != old);
 	return res >= 0 ? 1 : 0;
 }
@@ -67,8 +67,8 @@ static inline long ___down_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count += RWSEM_ACTIVE_WRITE_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -106,7 +106,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
  */
 static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
-	long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+	long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
 			   RWSEM_ACTIVE_WRITE_BIAS);
 	if (ret == RWSEM_UNLOCKED_VALUE)
 		return 1;
@@ -117,8 +117,8 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_ACTIVE_READ_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -142,8 +142,8 @@ static inline void __up_write(struct rw_semaphore *sem)
 {
 	long count;
 #ifndef	CONFIG_SMP
-	sem->count -= RWSEM_ACTIVE_WRITE_BIAS;
-	count = sem->count;
+	sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
+	count = sem->count.counter;
 #else
 	long temp;
 	__asm__ __volatile__(
@@ -171,8 +171,8 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
-	oldcount = sem->count;
-	sem->count -= RWSEM_WAITING_BIAS;
+	oldcount = sem->count.counter;
+	sem->count.counter -= RWSEM_WAITING_BIAS;
 #else
 	long temp;
 	__asm__ __volatile__(
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index 8b23e07..c5d544f 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -40,7 +40,7 @@
 static inline void
 __down_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count, 1);
+	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
 
 	if (result < 0)
 		rwsem_down_read_failed(sem);
@@ -55,9 +55,9 @@ ___down_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old + RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_acq(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
 
 	return old;
 }
@@ -85,7 +85,7 @@ __down_write_killable (struct rw_semaphore *sem)
 static inline void
 __up_read (struct rw_semaphore *sem)
 {
-	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count, -1);
+	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
 
 	if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -100,9 +100,9 @@ __up_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_ACTIVE_WRITE_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
 		rwsem_wake(sem);
@@ -115,8 +115,8 @@ static inline int
 __down_read_trylock (struct rw_semaphore *sem)
 {
 	long tmp;
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acq(&sem->count, tmp, tmp+1)) {
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
 			return 1;
 		}
 	}
@@ -129,8 +129,8 @@ __down_read_trylock (struct rw_semaphore *sem)
 static inline int
 __down_write_trylock (struct rw_semaphore *sem)
 {
-	long tmp = cmpxchg_acq(&sem->count, RWSEM_UNLOCKED_VALUE,
-			      RWSEM_ACTIVE_WRITE_BIAS);
+	long tmp = atomic_long_cmpxchg_acquire(&sem->count,
+			RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
 
@@ -143,9 +143,9 @@ __downgrade_write (struct rw_semaphore *sem)
 	long old, new;
 
 	do {
-		old = sem->count;
+		old = atomic_long_read(&sem->count);
 		new = old - RWSEM_WAITING_BIAS;
-	} while (cmpxchg_rel(&sem->count, old, new) != old);
+	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
 
 	if (old < 0)
 		rwsem_downgrade_wake(sem);
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index 3fc94a0..a3a93ec 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -41,8 +41,8 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	while ((tmp = sem->count) >= 0) {
-		if (tmp == cmpxchg_acquire(&sem->count, tmp,
+	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
+		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
 				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
@@ -79,7 +79,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
 		      RWSEM_ACTIVE_WRITE_BIAS);
 	return tmp == RWSEM_UNLOCKED_VALUE;
 }
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index d37fbb3..dd1d142 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -23,10 +23,11 @@ struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
 #include <linux/rwsem-spinlock.h> /* use a generic implementation */
+#define __RWSEM_INIT_COUNT(name)	.count = RWSEM_UNLOCKED_VALUE
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long count;
+	atomic_long_t count;
 	struct list_head wait_list;
 	raw_spinlock_t wait_lock;
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -54,9 +55,10 @@ extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
-	return sem->count != 0;
+	return atomic_long_read(&sem->count) != 0;
 }
 
+#define __RWSEM_INIT_COUNT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
 #endif
 
 /* Common initializer macros and functions */
@@ -74,7 +76,7 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
-	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	{ __RWSEM_INIT_COUNT(name),				\
 	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index b957da7..63b40a5 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -80,7 +80,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-	sem->count = RWSEM_UNLOCKED_VALUE;
+	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
@@ -153,10 +153,11 @@ __rwsem_mark_wake(struct rw_semaphore *sem,
 	if (wake_type != RWSEM_WAKE_READ_OWNED) {
 		adjustment = RWSEM_ACTIVE_READ_BIAS;
  try_reader_grant:
-		oldcount = rwsem_atomic_update(adjustment, sem) - adjustment;
+		oldcount = atomic_long_add_return(adjustment, &sem->count) - adjustment;
+
 		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
 			/* A writer stole the lock. Undo our reader grant. */
-			if (rwsem_atomic_update(-adjustment, sem) &
+			if (atomic_long_sub_return(adjustment, &sem->count) &
 						RWSEM_ACTIVE_MASK)
 				goto out;
 			/* Last active locker left. Retry waking readers. */
@@ -186,7 +187,7 @@ __rwsem_mark_wake(struct rw_semaphore *sem,
 		adjustment -= RWSEM_WAITING_BIAS;
 
 	if (adjustment)
-		rwsem_atomic_add(adjustment, sem);
+		atomic_long_add(adjustment, &sem->count);
 
 	next = sem->wait_list.next;
 	loop = woken;
@@ -233,7 +234,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	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);
+	count = atomic_long_add_return(adjustment, &sem->count);
 
 	/* If there are no active locks, wake the front queued process(es).
 	 *
@@ -282,7 +283,8 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 			RWSEM_ACTIVE_WRITE_BIAS :
 			RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
 
-	if (cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) {
+	if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count)
+							== RWSEM_WAITING_BIAS) {
 		rwsem_set_owner(sem);
 		return true;
 	}
@@ -296,13 +298,13 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = READ_ONCE(sem->count);
+	long old, count = atomic_long_read(&sem->count);
 
 	while (true) {
 		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
 			return false;
 
-		old = cmpxchg_acquire(&sem->count, count,
+		old = atomic_long_cmpxchg_acquire(&sem->count, count,
 				      count + RWSEM_ACTIVE_WRITE_BIAS);
 		if (old == count) {
 			rwsem_set_owner(sem);
@@ -324,7 +326,7 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 	rcu_read_lock();
 	owner = READ_ONCE(sem->owner);
 	if (!owner) {
-		long count = READ_ONCE(sem->count);
+		long count = atomic_long_read(&sem->count);
 		/*
 		 * If sem->owner is not set, yet we have just recently entered the
 		 * slowpath with the lock being active, then there is a possibility
@@ -375,7 +377,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
 	 * held by readers. Check the counter to verify the
 	 * state.
 	 */
-	count = READ_ONCE(sem->count);
+	count = atomic_long_read(&sem->count);
 	return (count == 0 || count == RWSEM_WAITING_BIAS);
 }
 
@@ -460,7 +462,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	WAKE_Q(wake_q);
 
 	/* undo write bias from down_write operation, stop active locking */
-	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
+	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
 
 	/* do optimistic spinning and steal lock if possible */
 	if (rwsem_optimistic_spin(sem))
@@ -483,7 +485,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 	/* we're now waiting on the lock, but no longer actively locking */
 	if (waiting) {
-		count = READ_ONCE(sem->count);
+		count = atomic_long_read(&sem->count);
 
 		/*
 		 * If there were already threads queued before us and there are
@@ -505,7 +507,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 		}
 
 	} else
-		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+		count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count);
 
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
@@ -521,7 +523,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 
 			schedule();
 			set_current_state(state);
-		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
+		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
@@ -536,7 +538,7 @@ out_nolock:
 	raw_spin_lock_irq(&sem->wait_lock);
 	list_del(&waiter.list);
 	if (list_empty(&sem->wait_list))
-		rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
 	else
 		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);

[PATCH v2 2/2] Remove rwsem_atomic_add() and rwsem_atomic_update()

[Jason Low]

The rwsem-xadd count has been converted to an atomic variable and the
rwsem code now directly uses atomic_long_add() and
atomic_long_add_return(), so we can remove the arch implementations of
rwsem_atomic_add() and rwsem_atomic_update().

Signed-off-by: Jason Low <jason.low2@hpe.com>
---
 arch/alpha/include/asm/rwsem.h | 42 ------------------------------------------
 arch/ia64/include/asm/rwsem.h  |  7 -------
 arch/s390/include/asm/rwsem.h  | 37 -------------------------------------
 arch/x86/include/asm/rwsem.h   | 18 ------------------
 include/asm-generic/rwsem.h    | 16 ----------------
 5 files changed, 120 deletions(-)

diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
index b40021a..77873d0 100644
--- a/arch/alpha/include/asm/rwsem.h
+++ b/arch/alpha/include/asm/rwsem.h
@@ -191,47 +191,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-static inline void rwsem_atomic_add(long val, struct rw_semaphore *sem)
-{
-#ifndef	CONFIG_SMP
-	sem->count += val;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%2,%0\n"
-	"	stq_c	%0,%1\n"
-	"	beq	%0,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (sem->count)
-	:"Ir" (val), "m" (sem->count));
-#endif
-}
-
-static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem)
-{
-#ifndef	CONFIG_SMP
-	sem->count += val;
-	return sem->count;
-#else
-	long ret, temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq 	%0,%3,%2\n"
-	"	addq	%0,%3,%0\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (ret), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (val), "m" (sem->count));
-
-	return ret;
-#endif
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ALPHA_RWSEM_H */
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index c5d544f..8fa98dd 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -151,11 +151,4 @@ __downgrade_write (struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * Implement atomic add functionality.  These used to be "inline" functions, but GCC v3.1
- * doesn't quite optimize this stuff right and ends up with bad calls to fetchandadd.
- */
-#define rwsem_atomic_add(delta, sem)	atomic64_add(delta, (atomic64_t *)(&(sem)->count))
-#define rwsem_atomic_update(delta, sem)	atomic64_add_return(delta, (atomic64_t *)(&(sem)->count))
-
 #endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index c75e447..597e7e9 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -207,41 +207,4 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	agr	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "d" (delta)
-		: "cc", "memory");
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	signed long old, new;
-
-	asm volatile(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	agr	%1,%4\n"
-		"	csg	%0,%1,%2\n"
-		"	jl	0b"
-		: "=&d" (old), "=&d" (new), "=Q" (sem->count)
-		: "Q" (sem->count), "d" (delta)
-		: "cc", "memory");
-	return new;
-}
-
 #endif /* _S390_RWSEM_H */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 453744c..089ced4 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -213,23 +213,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		     : "memory", "cc");
 }
 
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
-		     : "+m" (sem->count)
-		     : "er" (delta));
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return delta + xadd(&sem->count, delta);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index a3a93ec..5be122e 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -107,14 +107,6 @@ static inline void __up_write(struct rw_semaphore *sem)
 }
 
 /*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	atomic_long_add(delta, (atomic_long_t *)&sem->count);
-}
-
-/*
  * downgrade write lock to read lock
  */
 static inline void __downgrade_write(struct rw_semaphore *sem)
@@ -134,13 +126,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		rwsem_downgrade_wake(sem);
 }
 
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_GENERIC_RWSEM_H */
-- 
2.1.4