Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - Another attempt at enabling cross-release lockdep dependency
     tracking (automatically part of CONFIG_PROVE_LOCKING=y), this time
     with better performance and fewer false positives. (Byungchul Park)

   - Introduce lockdep_assert_irqs_enabled()/disabled() and convert
     open-coded equivalents to lockdep variants. (Frederic Weisbecker)

   - Add down_read_killable() and use it in the VFS's iterate_dir()
     method. (Kirill Tkhai)

   - Convert remaining uses of ACCESS_ONCE() to
     READ_ONCE()/WRITE_ONCE(). Most of the conversion was Coccinelle
     driven. (Mark Rutland, Paul E. McKenney)

   - Get rid of lockless_dereference(), by strengthening Alpha atomics,
     strengthening READ_ONCE() with smp_read_barrier_depends() and thus
     being able to convert users of lockless_dereference() to
     READ_ONCE(). (Will Deacon)

   - Various micro-optimizations:

        - better PV qspinlocks (Waiman Long),
        - better x86 barriers (Michael S. Tsirkin)
        - better x86 refcounts (Kees Cook)

   - ... plus other fixes and enhancements. (Borislav Petkov, Juergen
     Gross, Miguel Bernal Marin)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  locking/x86: Use LOCK ADD for smp_mb() instead of MFENCE
  rcu: Use lockdep to assert IRQs are disabled/enabled
  netpoll: Use lockdep to assert IRQs are disabled/enabled
  timers/posix-cpu-timers: Use lockdep to assert IRQs are disabled/enabled
  sched/clock, sched/cputime: Use lockdep to assert IRQs are disabled/enabled
  irq_work: Use lockdep to assert IRQs are disabled/enabled
  irq/timings: Use lockdep to assert IRQs are disabled/enabled
  perf/core: Use lockdep to assert IRQs are disabled/enabled
  x86: Use lockdep to assert IRQs are disabled/enabled
  smp/core: Use lockdep to assert IRQs are disabled/enabled
  timers/hrtimer: Use lockdep to assert IRQs are disabled/enabled
  timers/nohz: Use lockdep to assert IRQs are disabled/enabled
  workqueue: Use lockdep to assert IRQs are disabled/enabled
  irq/softirqs: Use lockdep to assert IRQs are disabled/enabled
  locking/lockdep: Add IRQs disabled/enabled assertion APIs: lockdep_assert_irqs_enabled()/disabled()
  locking/pvqspinlock: Implement hybrid PV queued/unfair locks
  locking/rwlocks: Fix comments
  x86/paravirt: Set up the virt_spin_lock_key after static keys get initialized
  block, locking/lockdep: Assign a lock_class per gendisk used for wait_for_completion()
  workqueue: Remove now redundant lock acquisitions wrt. workqueue flushes
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -709,6 +709,9 @@
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 
+	crossrelease_fullstack
+			[KNL] Allow to record full stack trace in cross-release
+
 	cryptomgr.notests
                         [KNL] Disable crypto self-tests
 

Documentation/filesystems/path-lookup.md

@@ -826,9 +826,9 @@ If the filesystem may need to revalidate dcache entries, then
 *is* passed the dentry but does not have access to the `inode` or the
 `seq` number from the `nameidata`, so it needs to be extra careful
 when accessing fields in the dentry.  This "extra care" typically
-involves using `ACCESS_ONCE()` or the newer [`READ_ONCE()`] to access
-fields, and verifying the result is not NULL before using it.  This
-pattern can be see in `nfs_lookup_revalidate()`.
+involves using [`READ_ONCE()`] to access fields, and verifying the
+result is not NULL before using it.  This pattern can be seen in
+`nfs_lookup_revalidate()`.
 
 A pair of patterns
 ------------------

Documentation/memory-barriers.txt

@@ -1880,18 +1880,6 @@ There are some more advanced barrier functions:
      See Documentation/atomic_{t,bitops}.txt for more information.
 
 
- (*) lockless_dereference();
-
-     This can be thought of as a pointer-fetch wrapper around the
-     smp_read_barrier_depends() data-dependency barrier.
-
-     This is also similar to rcu_dereference(), but in cases where
-     object lifetime is handled by some mechanism other than RCU, for
-     example, when the objects removed only when the system goes down.
-     In addition, lockless_dereference() is used in some data structures
-     that can be used both with and without RCU.
-
-
  (*) dma_wmb();
  (*) dma_rmb();
 

Documentation/translations/ko_KR/memory-barriers.txt

@@ -1858,18 +1858,6 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효
      참고하세요.
 
 
- (*) lockless_dereference();
-
-     이 함수는 smp_read_barrier_depends() 데이터 의존성 배리어를 사용하는
-     포인터 읽어오기 래퍼(wrapper) 함수로 생각될 수 있습니다.
-
-     객체의 라이프타임이 RCU 외의 메커니즘으로 관리된다는 점을 제외하면
-     rcu_dereference() 와도 유사한데, 예를 들면 객체가 시스템이 꺼질 때에만
-     제거되는 경우 등입니다.  또한, lockless_dereference() 은 RCU 와 함께
-     사용될수도, RCU 없이 사용될 수도 있는 일부 데이터 구조에 사용되고
-     있습니다.
-
-
  (*) dma_wmb();
  (*) dma_rmb();
 

arch/alpha/include/asm/atomic.h

@@ -14,6 +14,15 @@
  * than regular operations.
  */
 
+/*
+ * To ensure dependency ordering is preserved for the _relaxed and
+ * _release atomics, an smp_read_barrier_depends() is unconditionally
+ * inserted into the _relaxed variants, which are used to build the
+ * barriered versions. To avoid redundant back-to-back fences, we can
+ * define the _acquire and _fence versions explicitly.
+ */
+#define __atomic_op_acquire(op, args...)	op##_relaxed(args)
+#define __atomic_op_fence			__atomic_op_release
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -61,6 +70,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_read_barrier_depends();					\
 	return result;							\
 }
 
@@ -78,6 +88,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_read_barrier_depends();					\
 	return result;							\
 }
 
@@ -112,6 +123,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_read_barrier_depends();					\
 	return result;							\
 }
 
@@ -129,6 +141,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_read_barrier_depends();					\
 	return result;							\
 }
 

arch/alpha/include/asm/rwsem.h

@@ -22,7 +22,7 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-static inline void __down_read(struct rw_semaphore *sem)
+static inline int ___down_read(struct rw_semaphore *sem)
 {
 	long oldcount;
 #ifndef	CONFIG_SMP
@@ -42,10 +42,24 @@ static inline void __down_read(struct rw_semaphore *sem)
 	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
 	:"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
 #endif
-	if (unlikely(oldcount < 0))
+	return (oldcount < 0);
+}
+
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (unlikely(___down_read(sem)))
 		rwsem_down_read_failed(sem);
 }
 
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(___down_read(sem)))
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
+}
+
 /*
  * trylock for reading -- returns 1 if successful, 0 if contention
  */
@@ -95,9 +109,10 @@ static inline void __down_write(struct rw_semaphore *sem)
 
 static inline int __down_write_killable(struct rw_semaphore *sem)
 {
-	if (unlikely(___down_write(sem)))
+	if (unlikely(___down_write(sem))) {
 		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
 			return -EINTR;
+	}
 
 	return 0;
 }

arch/alpha/include/asm/spinlock.h

@@ -14,7 +14,6 @@
  * We make no fairness assumptions. They have a cost.
  */
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_is_locked(x)	((x)->lock != 0)
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
@@ -55,16 +54,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 /***********************************************************/
 
-static inline int arch_read_can_lock(arch_rwlock_t *lock)
-{
-	return (lock->lock & 1) == 0;
-}
-
-static inline int arch_write_can_lock(arch_rwlock_t *lock)
-{
-	return lock->lock == 0;
-}
-
 static inline void arch_read_lock(arch_rwlock_t *lock)
 {
 	long regx;
@@ -171,7 +160,4 @@ static inline void arch_write_unlock(arch_rwlock_t * lock)
 	lock->lock = 0;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* _ALPHA_SPINLOCK_H */

arch/arc/include/asm/spinlock.h

@@ -14,7 +14,6 @@
 #include <asm/barrier.h>
 
 #define arch_spin_is_locked(x)	((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__)
-#define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
@@ -410,14 +409,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
 #endif
 
-#define arch_read_can_lock(x)	((x)->counter > 0)
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
-#define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SPINLOCK_H */

arch/arc/kernel/smp.c

@@ -250,7 +250,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg)
 	 * and read back old value
 	 */
 	do {
-		new = old = ACCESS_ONCE(*ipi_data_ptr);
+		new = old = READ_ONCE(*ipi_data_ptr);
 		new |= 1U << msg;
 	} while (cmpxchg(ipi_data_ptr, old, new) != old);
 

arch/arm/include/asm/ptrace.h

@@ -126,8 +126,7 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 /*
  * kprobe-based event tracer support
  */
-#include <linux/stddef.h>
-#include <linux/types.h>
+#include <linux/compiler.h>
 #define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0))
 
 extern int regs_query_register_offset(const char *name);

arch/arm/include/asm/spinlock.h

@@ -53,8 +53,6 @@ static inline void dsb_sev(void)
  * memory.
  */
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
@@ -74,7 +72,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 
 	while (lockval.tickets.next != lockval.tickets.owner) {
 		wfe();
-		lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner);
+		lockval.tickets.owner = READ_ONCE(lock->tickets.owner);
 	}
 
 	smp_mb();
@@ -194,9 +192,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	dsb_sev();
 }
 
-/* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)
-
 /*
  * Read locks are a bit more hairy:
  *  - Exclusively load the lock value.
@@ -274,14 +269,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	}
 }
 
-/* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)
-
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SPINLOCK_H */

arch/arm/mach-tegra/cpuidle-tegra20.c

@@ -179,7 +179,7 @@ static int tegra20_idle_lp2_coupled(struct cpuidle_device *dev,
 	bool entered_lp2 = false;
 
 	if (tegra_pending_sgi())
-		ACCESS_ONCE(abort_flag) = true;
+		WRITE_ONCE(abort_flag, true);
 
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
 

arch/arm/vdso/vgettimeofday.c

@@ -35,7 +35,7 @@ static notrace u32 __vdso_read_begin(const struct vdso_data *vdata)
 {
 	u32 seq;
 repeat:
-	seq = ACCESS_ONCE(vdata->seq_count);
+	seq = READ_ONCE(vdata->seq_count);
 	if (seq & 1) {
 		cpu_relax();
 		goto repeat;

arch/arm64/Kconfig

@@ -22,7 +22,24 @@ config ARM64
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA
+	select ARCH_INLINE_READ_LOCK if !PREEMPT
+	select ARCH_INLINE_READ_LOCK_BH if !PREEMPT
+	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPT
+	select ARCH_INLINE_READ_UNLOCK if !PREEMPT
+	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPT
+	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_INLINE_WRITE_LOCK if !PREEMPT
+	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPT
+	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPT
+	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPT
+	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT
+	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING

arch/arm64/include/asm/Kbuild

@@ -16,6 +16,7 @@ generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msi.h
 generic-y += preempt.h
+generic-y += qrwlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += serial.h

arch/arm64/include/asm/spinlock.h

@@ -27,8 +27,6 @@
  * instructions.
  */
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
@@ -139,176 +137,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 }
 #define arch_spin_is_contended	arch_spin_is_contended
 
-/*
- * Write lock implementation.
- *
- * Write locks set bit 31. Unlocking, is done by writing 0 since the lock is
- * exclusively held.
- *
- * The memory barriers are implicit with the load-acquire and store-release
- * instructions.
- */
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	unsigned int tmp;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	sevl\n"
-	"1:	wfe\n"
-	"2:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1b\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 2b\n"
-	__nops(1),
-	/* LSE atomics */
-	"1:	mov	%w0, wzr\n"
-	"2:	casa	%w0, %w2, %1\n"
-	"	cbz	%w0, 3f\n"
-	"	ldxr	%w0, %1\n"
-	"	cbz	%w0, 2b\n"
-	"	wfe\n"
-	"	b	1b\n"
-	"3:")
-	: "=&r" (tmp), "+Q" (rw->lock)
-	: "r" (0x80000000)
-	: "memory");
-}
-
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
-	unsigned int tmp;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"1:	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 2f\n"
-	"	stxr	%w0, %w2, %1\n"
-	"	cbnz	%w0, 1b\n"
-	"2:",
-	/* LSE atomics */
-	"	mov	%w0, wzr\n"
-	"	casa	%w0, %w2, %1\n"
-	__nops(2))
-	: "=&r" (tmp), "+Q" (rw->lock)
-	: "r" (0x80000000)
-	: "memory");
-
-	return !tmp;
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	"	stlr	wzr, %0",
-	"	swpl	wzr, wzr, %0")
-	: "=Q" (rw->lock) :: "memory");
-}
-
-/* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x)		((x)->lock == 0)
-
-/*
- * Read lock implementation.
- *
- * It exclusively loads the lock value, increments it and stores the new value
- * back if positive and the CPU still exclusively owns the location. If the
- * value is negative, the lock is already held.
- *
- * During unlocking there may be multiple active read locks but no write lock.
- *
- * The memory barriers are implicit with the load-acquire and store-release
- * instructions.
- *
- * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC
- * and LSE implementations may exhibit different behaviour (although this
- * will have no effect on lockdep).
- */
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	unsigned int tmp, tmp2;
-
-	asm volatile(
-	"	sevl\n"
-	ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"1:	wfe\n"
-	"2:	ldaxr	%w0, %2\n"
-	"	add	%w0, %w0, #1\n"
-	"	tbnz	%w0, #31, 1b\n"
-	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 2b\n"
-	__nops(1),
-	/* LSE atomics */
-	"1:	wfe\n"
-	"2:	ldxr	%w0, %2\n"
-	"	adds	%w1, %w0, #1\n"
-	"	tbnz	%w1, #31, 1b\n"
-	"	casa	%w0, %w1, %2\n"
-	"	sbc	%w0, %w1, %w0\n"
-	"	cbnz	%w0, 2b")
-	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
-	:
-	: "cc", "memory");
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	unsigned int tmp, tmp2;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"1:	ldxr	%w0, %2\n"
-	"	sub	%w0, %w0, #1\n"
-	"	stlxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b",
-	/* LSE atomics */
-	"	movn	%w0, #0\n"
-	"	staddl	%w0, %2\n"
-	__nops(2))
-	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
-	:
-	: "memory");
-}
-
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	unsigned int tmp, tmp2;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	mov	%w1, #1\n"
-	"1:	ldaxr	%w0, %2\n"
-	"	add	%w0, %w0, #1\n"
-	"	tbnz	%w0, #31, 2f\n"
-	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	"2:",
-	/* LSE atomics */
-	"	ldr	%w0, %2\n"
-	"	adds	%w1, %w0, #1\n"
-	"	tbnz	%w1, #31, 1f\n"
-	"	casa	%w0, %w1, %2\n"
-	"	sbc	%w1, %w1, %w0\n"
-	__nops(1)
-	"1:")
-	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
-	:
-	: "cc", "memory");
-
-	return !tmp2;
-}
-
-/* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x)		((x)->lock < 0x80000000)
-
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
+#include <asm/qrwlock.h>
 
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()

arch/arm64/include/asm/spinlock_types.h

@@ -36,10 +36,6 @@ typedef struct {
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 , 0 }
 
-typedef struct {
-	volatile unsigned int lock;
-} arch_rwlock_t;
-
-#define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
+#include <asm-generic/qrwlock_types.h>
 
 #endif

arch/blackfin/include/asm/spinlock.h

@@ -36,8 +36,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__raw_spin_lock_asm(&lock->lock);
 }
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	return __raw_spin_trylock_asm(&lock->lock);
@@ -48,23 +46,11 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	__raw_spin_unlock_asm(&lock->lock);
 }
 
-static inline int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	return __raw_uncached_fetch_asm(&rw->lock) > 0;
-}
-
-static inline int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	return __raw_uncached_fetch_asm(&rw->lock) == RW_LOCK_BIAS;
-}
-
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	__raw_read_lock_asm(&rw->lock);
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	return __raw_read_trylock_asm(&rw->lock);
@@ -80,8 +66,6 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	__raw_write_lock_asm(&rw->lock);
 }
 
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	return __raw_write_trylock_asm(&rw->lock);
@@ -92,10 +76,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	__raw_write_unlock_asm(&rw->lock);
 }
 
-#define arch_spin_relax(lock)  	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif
 
 #endif /*  !__BFIN_SPINLOCK_H */

arch/hexagon/include/asm/spinlock.h

@@ -86,16 +86,6 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
 	return temp;
 }
 
-static inline int arch_read_can_lock(arch_rwlock_t *rwlock)
-{
-	return rwlock->lock == 0;
-}
-
-static inline int arch_write_can_lock(arch_rwlock_t *rwlock)
-{
-	return rwlock->lock == 0;
-}
-
 /*  Stuffs a -1 in the lock value?  */
 static inline void arch_write_lock(arch_rwlock_t *lock)
 {
@@ -177,11 +167,6 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 /*
  * SMP spinlocks are intended to allow only a single CPU at the lock
  */
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 #define arch_spin_is_locked(x) ((x)->lock != 0)
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif

arch/ia64/include/asm/rwsem.h

@@ -38,15 +38,31 @@
 /*
  * lock for reading
  */
-static inline void
-__down_read (struct rw_semaphore *sem)
+static inline int
+___down_read (struct rw_semaphore *sem)
 {
 	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
 
-	if (result < 0)
+	return (result < 0);
+}
+
+static inline void
+__down_read (struct rw_semaphore *sem)
+{
+	if (___down_read(sem))
 		rwsem_down_read_failed(sem);
 }
 
+static inline int
+__down_read_killable (struct rw_semaphore *sem)
+{
+	if (___down_read(sem))
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+
+	return 0;
+}
+
 /*
  * lock for writing
  */
@@ -73,9 +89,10 @@ __down_write (struct rw_semaphore *sem)
 static inline int
 __down_write_killable (struct rw_semaphore *sem)
 {
-	if (___down_write(sem))
+	if (___down_write(sem)) {
 		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
 			return -EINTR;
+	}
 
 	return 0;
 }

arch/ia64/include/asm/spinlock.h

@@ -62,7 +62,7 @@ static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 
 static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
-	int tmp = ACCESS_ONCE(lock->lock);
+	int tmp = READ_ONCE(lock->lock);
 
 	if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK))
 		return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp;
@@ -74,19 +74,19 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
 	asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p));
-	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
+	WRITE_ONCE(*p, (tmp + 2) & ~1);
 }
 
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
-	long tmp = ACCESS_ONCE(lock->lock);
+	long tmp = READ_ONCE(lock->lock);
 
 	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK);
 }
 
 static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
-	long tmp = ACCESS_ONCE(lock->lock);
+	long tmp = READ_ONCE(lock->lock);
 
 	return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1;
 }
@@ -127,9 +127,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 {
 	arch_spin_lock(lock);
 }
-
-#define arch_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
-#define arch_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
+#define arch_spin_lock_flags	arch_spin_lock_flags
 
 #ifdef ASM_SUPPORTED
 
@@ -157,6 +155,7 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "p6", "p7", "r2", "memory");
 }
 
+#define arch_read_lock_flags arch_read_lock_flags
 #define arch_read_lock(lock) arch_read_lock_flags(lock, 0)
 
 #else /* !ASM_SUPPORTED */
@@ -209,6 +208,7 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 		: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
 }
 
+#define arch_write_lock_flags arch_write_lock_flags
 #define arch_write_lock(rw) arch_write_lock_flags(rw, 0)
 
 #define arch_write_trylock(rw)							\
@@ -232,8 +232,6 @@ static inline void arch_write_unlock(arch_rwlock_t *x)
 
 #else /* !ASM_SUPPORTED */
 
-#define arch_write_lock_flags(l, flags) arch_write_lock(l)
-
 #define arch_write_lock(l)								\
 ({											\
 	__u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1);			\
@@ -273,8 +271,4 @@ static inline int arch_read_trylock(arch_rwlock_t *x)
 	return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word;
 }
 
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /*  _ASM_IA64_SPINLOCK_H */

arch/m32r/include/asm/spinlock.h

@@ -29,7 +29,6 @@
  */
 
 #define arch_spin_is_locked(x)		(*(volatile int *)(&(x)->slock) <= 0)
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 /**
  * arch_spin_trylock - Try spin lock and return a result
@@ -138,18 +137,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
  * semaphore.h for details.  -ben
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_read_can_lock(x) ((int)(x)->lock > 0)
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS)
-
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp0, tmp1;
@@ -318,11 +305,4 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 	return 0;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif	/* _ASM_M32R_SPINLOCK_H */

arch/metag/include/asm/spinlock.h

@@ -16,13 +16,4 @@
  * locked.
  */
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
-#define	arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define	arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SPINLOCK_H */

arch/metag/include/asm/spinlock_lnkget.h

@@ -137,21 +137,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 		      : "memory");
 }
 
-/* write_can_lock - would write_trylock() succeed? */
-static inline int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	int ret;
-
-	asm volatile ("LNKGETD	%0, [%1]\n"
-		      "CMP	%0, #0\n"
-		      "MOV	%0, #1\n"
-		      "XORNZ     %0, %0, %0\n"
-		      : "=&d" (ret)
-		      : "da" (&rw->lock)
-		      : "cc");
-	return ret;
-}
-
 /*
  * Read locks are a bit more hairy:
  *  - Exclusively load the lock value.
@@ -225,26 +210,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	return tmp;
 }
 
-/* read_can_lock - would read_trylock() succeed? */
-static inline int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	int tmp;
-
-	asm volatile ("LNKGETD	%0, [%1]\n"
-		      "CMP	%0, %2\n"
-		      "MOV	%0, #1\n"
-		      "XORZ	%0, %0, %0\n"
-		      : "=&d" (tmp)
-		      : "da" (&rw->lock), "bd" (0x80000000)
-		      : "cc");
-	return tmp;
-}
-
-#define	arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define	arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SPINLOCK_LNKGET_H */

arch/metag/include/asm/spinlock_lock1.h

@@ -105,16 +105,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	rw->lock = 0;
 }
 
-/* write_can_lock - would write_trylock() succeed? */
-static inline int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	unsigned int ret;
-
-	barrier();
-	ret = rw->lock;
-	return (ret == 0);
-}
-
 /*
  * Read locks are a bit more hairy:
  *  - Exclusively load the lock value.
@@ -172,14 +162,4 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	return (ret < 0x80000000);
 }
 
-/* read_can_lock - would read_trylock() succeed? */
-static inline int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	unsigned int ret;
-
-	barrier();
-	ret = rw->lock;
-	return (ret < 0x80000000);
-}
-
 #endif /* __ASM_SPINLOCK_LOCK1_H */

arch/mips/include/asm/spinlock.h

@@ -13,11 +13,4 @@
 #include <asm/qrwlock.h>
 #include <asm/qspinlock.h>
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* _ASM_SPINLOCK_H */

arch/mips/include/asm/vdso.h

@@ -99,7 +99,7 @@ static inline u32 vdso_data_read_begin(const union mips_vdso_data *data)
 	u32 seq;
 
 	while (true) {
-		seq = ACCESS_ONCE(data->seq_count);
+		seq = READ_ONCE(data->seq_count);
 		if (likely(!(seq & 1))) {
 			/* Paired with smp_wmb() in vdso_data_write_*(). */
 			smp_rmb();

arch/mips/kernel/pm-cps.c

@@ -166,7 +166,7 @@ int cps_pm_enter_state(enum cps_pm_state state)
 	nc_core_ready_count = nc_addr;
 
 	/* Ensure ready_count is zero-initialised before the assembly runs */
-	ACCESS_ONCE(*nc_core_ready_count) = 0;
+	WRITE_ONCE(*nc_core_ready_count, 0);
 	coupled_barrier(&per_cpu(pm_barrier, core), online);
 
 	/* Run the generated entry code */

arch/mn10300/include/asm/spinlock.h

@@ -84,6 +84,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 		: "d" (flags), "a"(&lock->slock), "i"(EPSW_IE | MN10300_CLI_LEVEL)
 		: "memory", "cc");
 }
+#define arch_spin_lock_flags	arch_spin_lock_flags
 
 #ifdef __KERNEL__
 
@@ -98,18 +99,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock,
  * read-locks.
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_read_can_lock(x) ((int)(x)->lock > 0)
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS)
-
 /*
  * On mn10300, we implement read-write locks as a 32-bit counter
  * with the high bit (sign) being the "contended" bit.
@@ -183,9 +172,6 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 	return 0;
 }
 
-#define arch_read_lock_flags(lock, flags)  arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()

arch/mn10300/kernel/mn10300-serial.c

@@ -543,7 +543,7 @@ static void mn10300_serial_receive_interrupt(struct mn10300_serial_port *port)
 
 try_again:
 	/* pull chars out of the hat */
-	ix = ACCESS_ONCE(port->rx_outp);
+	ix = READ_ONCE(port->rx_outp);
 	if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0) {
 		if (push && !tport->low_latency)
 			tty_flip_buffer_push(tport);
@@ -1724,7 +1724,7 @@ static int mn10300_serial_poll_get_char(struct uart_port *_port)
 	if (mn10300_serial_int_tbl[port->rx_irq].port != NULL) {
 		do {
 			/* pull chars out of the hat */
-			ix = ACCESS_ONCE(port->rx_outp);
+			ix = READ_ONCE(port->rx_outp);
 			if (CIRC_CNT(port->rx_inp, ix, MNSC_BUFFER_SIZE) == 0)
 				return NO_POLL_CHAR;
 

arch/parisc/include/asm/atomic.h

@@ -261,7 +261,7 @@ atomic64_set(atomic64_t *v, s64 i)
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
-	return ACCESS_ONCE((v)->counter);
+	return READ_ONCE((v)->counter);
 }
 
 #define atomic64_inc(v)		(atomic64_add(   1,(v)))

arch/parisc/include/asm/spinlock.h

@@ -32,6 +32,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 				cpu_relax();
 	mb();
 }
+#define arch_spin_lock_flags arch_spin_lock_flags
 
 static inline void arch_spin_unlock(arch_spinlock_t *x)
 {
@@ -169,25 +170,4 @@ static __inline__ int arch_write_trylock(arch_rwlock_t *rw)
 	return result;
 }
 
-/*
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static __inline__ int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	return rw->counter >= 0;
-}
-
-/*
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static __inline__ int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	return !rw->counter;
-}
-
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* __ASM_SPINLOCK_H */

arch/powerpc/include/asm/spinlock.h

@@ -161,6 +161,7 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 		local_irq_restore(flags_dis);
 	}
 }
+#define arch_spin_lock_flags arch_spin_lock_flags
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
@@ -181,9 +182,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
  * read-locks.
  */
 
-#define arch_read_can_lock(rw)		((rw)->lock >= 0)
-#define arch_write_can_lock(rw)	(!(rw)->lock)
-
 #ifdef CONFIG_PPC64
 #define __DO_SIGN_EXTEND	"extsw	%0,%0\n"
 #define WRLOCK_TOKEN		LOCK_TOKEN	/* it's negative */
@@ -302,9 +300,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	rw->lock = 0;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #define arch_spin_relax(lock)	__spin_yield(lock)
 #define arch_read_relax(lock)	__rw_yield(lock)
 #define arch_write_relax(lock)	__rw_yield(lock)

arch/powerpc/kernel/rtas.c

@@ -78,7 +78,7 @@ static unsigned long lock_rtas(void)
 
 	local_irq_save(flags);
 	preempt_disable();
-	arch_spin_lock_flags(&rtas.lock, flags);
+	arch_spin_lock(&rtas.lock);
 	return flags;
 }
 

arch/powerpc/platforms/powernv/opal-msglog.c

@@ -43,7 +43,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 	if (!opal_memcons)
 		return -ENODEV;
 
-	out_pos = be32_to_cpu(ACCESS_ONCE(opal_memcons->out_pos));
+	out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos));
 
 	/* Now we've read out_pos, put a barrier in before reading the new
 	 * data it points to in conbuf. */

arch/s390/include/asm/spinlock.h

@@ -38,6 +38,7 @@ bool arch_vcpu_is_preempted(int cpu);
  */
 
 void arch_spin_relax(arch_spinlock_t *lock);
+#define arch_spin_relax	arch_spin_relax
 
 void arch_spin_lock_wait(arch_spinlock_t *);
 int arch_spin_trylock_retry(arch_spinlock_t *);
@@ -76,6 +77,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
 	if (!arch_spin_trylock_once(lp))
 		arch_spin_lock_wait(lp);
 }
+#define arch_spin_lock_flags	arch_spin_lock_flags
 
 static inline int arch_spin_trylock(arch_spinlock_t *lp)
 {
@@ -105,20 +107,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
  * read-locks.
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_read_can_lock(x) (((x)->cnts & 0xffff0000) == 0)
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_write_can_lock(x) ((x)->cnts == 0)
-
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 #define arch_read_relax(rw) barrier()
 #define arch_write_relax(rw) barrier()
 

arch/s390/lib/spinlock.c

@@ -215,7 +215,7 @@ static inline void arch_spin_lock_classic(arch_spinlock_t *lp)
 	lockval = SPINLOCK_LOCKVAL;	/* cpu + 1 */
 
 	/* Pass the virtual CPU to the lock holder if it is not running */
-	owner = arch_spin_yield_target(ACCESS_ONCE(lp->lock), NULL);
+	owner = arch_spin_yield_target(READ_ONCE(lp->lock), NULL);
 	if (owner && arch_vcpu_is_preempted(owner - 1))
 		smp_yield_cpu(owner - 1);
 

arch/sh/include/asm/spinlock-cas.h

@@ -27,7 +27,6 @@ static inline unsigned __sl_cas(volatile unsigned *p, unsigned old, unsigned new
  */
 
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
@@ -53,18 +52,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
  * read-locks.
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_read_can_lock(x)	((x)->lock > 0)
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
-
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned old;
@@ -102,11 +89,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	return __sl_cas(&rw->lock, RW_LOCK_BIAS, 0) == RW_LOCK_BIAS;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SH_SPINLOCK_CAS_H */

arch/sh/include/asm/spinlock-llsc.h

@@ -19,7 +19,6 @@
  */
 
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
@@ -89,18 +88,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
  * read-locks.
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_read_can_lock(x)	((x)->lock > 0)
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-#define arch_write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
-
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
@@ -209,11 +196,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	return (oldval > (RW_LOCK_BIAS - 1));
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* __ASM_SH_SPINLOCK_LLSC_H */

arch/sparc/include/asm/atomic_32.h

@@ -32,7 +32,7 @@ void atomic_set(atomic_t *, int);
 
 #define atomic_set_release(v, i)	atomic_set((v), (i))
 
-#define atomic_read(v)          ACCESS_ONCE((v)->counter)
+#define atomic_read(v)          READ_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))

arch/sparc/include/asm/ptrace.h

@@ -7,6 +7,7 @@
 #if defined(__sparc__) && defined(__arch64__)
 #ifndef __ASSEMBLY__
 
+#include <linux/compiler.h>
 #include <linux/threads.h>
 #include <asm/switch_to.h>
 

arch/sparc/include/asm/spinlock_32.h

@@ -183,17 +183,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw)
 	res; \
 })
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_read_lock_flags(rw, flags)   arch_read_lock(rw)
-#define arch_write_lock_flags(rw, flags)  arch_write_lock(rw)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
-#define arch_read_can_lock(rw) (!((rw)->lock & 0xff))
-#define arch_write_can_lock(rw) (!(rw)->lock)
-
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* __SPARC_SPINLOCK_H */

arch/sparc/include/asm/spinlock_64.h

@@ -14,13 +14,6 @@
 #include <asm/qrwlock.h>
 #include <asm/qspinlock.h>
 
-#define arch_read_lock_flags(p, f) arch_read_lock(p)
-#define arch_write_lock_flags(p, f) arch_write_lock(p)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_SPINLOCK_H) */

arch/tile/gxio/dma_queue.c

@@ -163,14 +163,14 @@ int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue,
 				 int64_t completion_slot, int update)
 {
 	if (update) {
-		if (ACCESS_ONCE(dma_queue->hw_complete_count) >
+		if (READ_ONCE(dma_queue->hw_complete_count) >
 		    completion_slot)
 			return 1;
 
 		__gxio_dma_queue_update_credits(dma_queue);
 	}
 
-	return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot;
+	return READ_ONCE(dma_queue->hw_complete_count) > completion_slot;
 }
 
 EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete);

arch/tile/include/asm/spinlock_32.h

@@ -51,9 +51,6 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 
 void arch_spin_lock(arch_spinlock_t *lock);
 
-/* We cannot take an interrupt after getting a ticket, so don't enable them. */
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 int arch_spin_trylock(arch_spinlock_t *lock);
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
@@ -79,22 +76,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define _RD_COUNT_SHIFT 24
 #define _RD_COUNT_WIDTH 8
 
-/**
- * arch_read_can_lock() - would read_trylock() succeed?
- */
-static inline int arch_read_can_lock(arch_rwlock_t *rwlock)
-{
-	return (rwlock->lock << _RD_COUNT_WIDTH) == 0;
-}
-
-/**
- * arch_write_can_lock() - would write_trylock() succeed?
- */
-static inline int arch_write_can_lock(arch_rwlock_t *rwlock)
-{
-	return rwlock->lock == 0;
-}
-
 /**
  * arch_read_lock() - acquire a read lock.
  */
@@ -125,7 +106,4 @@ void arch_read_unlock(arch_rwlock_t *rwlock);
  */
 void arch_write_unlock(arch_rwlock_t *rwlock);
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* _ASM_TILE_SPINLOCK_32_H */

arch/tile/include/asm/spinlock_64.h

@@ -75,9 +75,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 /* Try to get the lock, and return whether we succeeded. */
 int arch_spin_trylock(arch_spinlock_t *lock);
 
-/* We cannot take an interrupt after getting a ticket, so don't enable them. */
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -93,24 +90,6 @@ static inline int arch_write_val_locked(int val)
 	return val < 0;  /* Optimize "val & __WRITE_LOCK_BIT". */
 }
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_read_can_lock(arch_rwlock_t *rw)
-{
-	return !arch_write_val_locked(rw->lock);
-}
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_write_can_lock(arch_rwlock_t *rw)
-{
-	return rw->lock == 0;
-}
-
 extern void __read_lock_failed(arch_rwlock_t *rw);
 
 static inline void arch_read_lock(arch_rwlock_t *rw)
@@ -156,7 +135,4 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	return 0;
 }
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
 #endif /* _ASM_TILE_SPINLOCK_64_H */

arch/tile/include/gxio/dma_queue.h

@@ -121,7 +121,7 @@ static inline int64_t __gxio_dma_queue_reserve(__gxio_dma_queue_t *dma_queue,
 		 * if the result is LESS than "hw_complete_count".
 		 */
 		uint64_t complete;
-		complete = ACCESS_ONCE(dma_queue->hw_complete_count);
+		complete = READ_ONCE(dma_queue->hw_complete_count);
 		slot |= (complete & 0xffffffffff000000);
 		if (slot < complete)
 			slot += 0x1000000;

arch/tile/kernel/ptrace.c

@@ -255,7 +255,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 int do_syscall_trace_enter(struct pt_regs *regs)
 {
-	u32 work = ACCESS_ONCE(current_thread_info()->flags);
+	u32 work = READ_ONCE(current_thread_info()->flags);
 
 	if ((work & _TIF_SYSCALL_TRACE) &&
 	    tracehook_report_syscall_entry(regs)) {

arch/um/include/shared/init.h

@@ -41,7 +41,7 @@
 typedef int (*initcall_t)(void);
 typedef void (*exitcall_t)(void);
 
-#include <linux/compiler.h>
+#include <linux/compiler_types.h>
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */

arch/x86/Kconfig

@@ -56,7 +56,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_PMEM_API		if X86_64
 	# Causing hangs/crashes, see the commit that added this change for details.
-	select ARCH_HAS_REFCOUNT		if BROKEN
+	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN

arch/x86/entry/common.c

@@ -75,7 +75,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
 		BUG_ON(regs != task_pt_regs(current));
 
-	work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
+	work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
 	if (unlikely(work & _TIF_SYSCALL_EMU))
 		emulated = true;
@@ -186,9 +186,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 
 	addr_limit_user_check();
 
-	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
-		local_irq_disable();
-
+	lockdep_assert_irqs_disabled();
 	lockdep_sys_exit();
 
 	cached_flags = READ_ONCE(ti->flags);

arch/x86/entry/vdso/vclock_gettime.c

@@ -318,7 +318,7 @@ int gettimeofday(struct timeval *, struct timezone *)
 notrace time_t __vdso_time(time_t *t)
 {
 	/* This is atomic on x86 so we don't need any locks. */
-	time_t result = ACCESS_ONCE(gtod->wall_time_sec);
+	time_t result = READ_ONCE(gtod->wall_time_sec);
 
 	if (t)
 		*t = result;

arch/x86/events/core.c

@@ -2118,7 +2118,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (ACCESS_ONCE(x86_pmu.attr_rdpmc))
+	if (READ_ONCE(x86_pmu.attr_rdpmc))
 		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
 	return err;
@@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment)
 		struct ldt_struct *ldt;
 
 		/* IRQs are off, so this synchronizes with smp_store_release */
-		ldt = lockless_dereference(current->active_mm->context.ldt);
+		ldt = READ_ONCE(current->active_mm->context.ldt);
 		if (!ldt || idx >= ldt->nr_entries)
 			return 0;
 

arch/x86/include/asm/barrier.h

@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define mb() 	asm volatile("mfence":::"memory")
@@ -31,7 +31,11 @@
 #endif
 #define dma_wmb()	barrier()
 
-#define __smp_mb()	mb()
+#ifdef CONFIG_X86_32
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc")
+#else
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc")
+#endif
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)

arch/x86/include/asm/mmu_context.h

@@ -73,8 +73,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 
-	/* lockless_dereference synchronizes with smp_store_release */
-	ldt = lockless_dereference(mm->context.ldt);
+	/* READ_ONCE synchronizes with smp_store_release */
+	ldt = READ_ONCE(mm->context.ldt);
 
 	/*
 	 * Any change to mm->context.ldt is followed by an IPI to all

arch/x86/include/asm/qspinlock.h

@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_QSPINLOCK_H
 #define _ASM_X86_QSPINLOCK_H
 
+#include <linux/jump_label.h>
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
@@ -47,10 +48,14 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 #endif
 
 #ifdef CONFIG_PARAVIRT
+DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
+
+void native_pv_lock_init(void) __init;
+
 #define virt_spin_lock virt_spin_lock
 static inline bool virt_spin_lock(struct qspinlock *lock)
 {
-	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+	if (!static_branch_likely(&virt_spin_lock_key))
 		return false;
 
 	/*
@@ -66,6 +71,10 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
 
 	return true;
 }
+#else
+static inline void native_pv_lock_init(void)
+{
+}
 #endif /* CONFIG_PARAVIRT */
 
 #include <asm-generic/qspinlock.h>

arch/x86/include/asm/refcount.h

@@ -15,7 +15,7 @@
  * back to the regular execution flow in .text.
  */
 #define _REFCOUNT_EXCEPTION				\
-	".pushsection .text.unlikely\n"			\
+	".pushsection .text..refcount\n"		\
 	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
 	"112:\t" ASM_UD0 "\n"				\
 	ASM_UNREACHABLE					\

arch/x86/include/asm/rwsem.h

@@ -61,18 +61,33 @@
 /*
  * lock for reading
  */
+#define ____down_read(sem, slow_path)					\
+({									\
+	struct rw_semaphore* ret;					\
+	asm volatile("# beginning down_read\n\t"			\
+		     LOCK_PREFIX _ASM_INC "(%[sem])\n\t"		\
+		     /* adds 0x00000001 */				\
+		     "  jns        1f\n"				\
+		     "  call " slow_path "\n"				\
+		     "1:\n\t"						\
+		     "# ending down_read\n\t"				\
+		     : "+m" (sem->count), "=a" (ret),			\
+			ASM_CALL_CONSTRAINT				\
+		     : [sem] "a" (sem)					\
+		     : "memory", "cc");					\
+	ret;								\
+})
+
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	asm volatile("# beginning down_read\n\t"
-		     LOCK_PREFIX _ASM_INC "(%1)\n\t"
-		     /* adds 0x00000001 */
-		     "  jns        1f\n"
-		     "  call call_rwsem_down_read_failed\n"
-		     "1:\n\t"
-		     "# ending down_read\n\t"
-		     : "+m" (sem->count)
-		     : "a" (sem)
-		     : "memory", "cc");
+	____down_read(sem, "call_rwsem_down_read_failed");
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable")))
+		return -EINTR;
+	return 0;
 }
 
 /*
@@ -82,17 +97,18 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 {
 	long result, tmp;
 	asm volatile("# beginning __down_read_trylock\n\t"
-		     "  mov          %0,%1\n\t"
+		     "  mov          %[count],%[result]\n\t"
 		     "1:\n\t"
-		     "  mov          %1,%2\n\t"
-		     "  add          %3,%2\n\t"
+		     "  mov          %[result],%[tmp]\n\t"
+		     "  add          %[inc],%[tmp]\n\t"
 		     "  jle	     2f\n\t"
-		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
+		     LOCK_PREFIX "  cmpxchg  %[tmp],%[count]\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
 		     "# ending __down_read_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
-		     : "i" (RWSEM_ACTIVE_READ_BIAS)
+		     : [count] "+m" (sem->count), [result] "=&a" (result),
+		       [tmp] "=&r" (tmp)
+		     : [inc] "i" (RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
 	return result >= 0;
 }
@@ -106,7 +122,7 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 	struct rw_semaphore* ret;			\
 							\
 	asm volatile("# beginning down_write\n\t"	\
-		     LOCK_PREFIX "  xadd      %1,(%4)\n\t"	\
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"	\
 		     /* adds 0xffff0001, returns the old value */ \
 		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
 		     /* was the active mask 0 before? */\
@@ -114,9 +130,9 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 		     "  call " slow_path "\n"		\
 		     "1:\n"				\
 		     "# ending down_write"		\
-		     : "+m" (sem->count), "=d" (tmp),	\
+		     : "+m" (sem->count), [tmp] "=d" (tmp),	\
 		       "=a" (ret), ASM_CALL_CONSTRAINT	\
-		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
+		     : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \
 		     : "memory", "cc");			\
 	ret;						\
 })
@@ -142,21 +158,21 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem)
 	bool result;
 	long tmp0, tmp1;
 	asm volatile("# beginning __down_write_trylock\n\t"
-		     "  mov          %0,%1\n\t"
+		     "  mov          %[count],%[tmp0]\n\t"
 		     "1:\n\t"
 		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
 		     /* was the active mask 0 before? */
 		     "  jnz          2f\n\t"
-		     "  mov          %1,%2\n\t"
-		     "  add          %4,%2\n\t"
-		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
+		     "  mov          %[tmp0],%[tmp1]\n\t"
+		     "  add          %[inc],%[tmp1]\n\t"
+		     LOCK_PREFIX "  cmpxchg  %[tmp1],%[count]\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
 		     CC_SET(e)
 		     "# ending __down_write_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
-		       CC_OUT(e) (result)
-		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
+		     : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0),
+		       [tmp1] "=&r" (tmp1), CC_OUT(e) (result)
+		     : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory");
 	return result;
 }
@@ -168,14 +184,14 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long tmp;
 	asm volatile("# beginning __up_read\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
 		     /* subtracts 1, returns the old value */
 		     "  jns        1f\n\t"
 		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n"
 		     "# ending __up_read\n"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS)
+		     : "+m" (sem->count), [tmp] "=d" (tmp)
+		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
 }
 
@@ -186,14 +202,14 @@ static inline void __up_write(struct rw_semaphore *sem)
 {
 	long tmp;
 	asm volatile("# beginning __up_write\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
 		     /* subtracts 0xffff0001, returns the old value */
 		     "  jns        1f\n\t"
 		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n\t"
 		     "# ending __up_write\n"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+		     : "+m" (sem->count), [tmp] "=d" (tmp)
+		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 }
 
@@ -203,7 +219,7 @@ static inline void __up_write(struct rw_semaphore *sem)
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	asm volatile("# beginning __downgrade_write\n\t"
-		     LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t"
+		     LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t"
 		     /*
 		      * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
 		      *     0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
@@ -213,7 +229,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		     "1:\n\t"
 		     "# ending __downgrade_write\n"
 		     : "+m" (sem->count)
-		     : "a" (sem), "er" (-RWSEM_WAITING_BIAS)
+		     : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS)
 		     : "memory", "cc");
 }
 

arch/x86/include/asm/spinlock.h

@@ -42,11 +42,4 @@
 
 #include <asm/qrwlock.h>
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* _ASM_X86_SPINLOCK_H */

arch/x86/include/asm/vgtod.h

@@ -49,7 +49,7 @@ static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
 	unsigned ret;
 
 repeat:
-	ret = ACCESS_ONCE(s->seq);
+	ret = READ_ONCE(s->seq);
 	if (unlikely(ret & 1)) {
 		cpu_relax();
 		goto repeat;

arch/x86/kernel/espfix_64.c

@@ -155,14 +155,14 @@ void init_espfix_ap(int cpu)
 	page = cpu/ESPFIX_STACKS_PER_PAGE;
 
 	/* Did another CPU already set this up? */
-	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	stack_page = READ_ONCE(espfix_pages[page]);
 	if (likely(stack_page))
 		goto done;
 
 	mutex_lock(&espfix_init_mutex);
 
 	/* Did we race on the lock? */
-	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	stack_page = READ_ONCE(espfix_pages[page]);
 	if (stack_page)
 		goto unlock_done;
 
@@ -200,7 +200,7 @@ void init_espfix_ap(int cpu)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 
 	/* Job is done for this CPU and any CPU which shares this page */
-	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+	WRITE_ONCE(espfix_pages[page], stack_page);
 
 unlock_done:
 	mutex_unlock(&espfix_init_mutex);

arch/x86/kernel/ldt.c

@@ -102,7 +102,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt)
 static void install_ldt(struct mm_struct *current_mm,
 			struct ldt_struct *ldt)
 {
-	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	/* Synchronizes with READ_ONCE in load_mm_ldt. */
 	smp_store_release(&current_mm->context.ldt, ldt);
 
 	/* Activate the LDT for all CPUs using current_mm. */

arch/x86/kernel/nmi.c

@@ -105,7 +105,7 @@ static void nmi_max_handler(struct irq_work *w)
 {
 	struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
 	int remainder_ns, decimal_msecs;
-	u64 whole_msecs = ACCESS_ONCE(a->max_duration);
+	u64 whole_msecs = READ_ONCE(a->max_duration);
 
 	remainder_ns = do_div(whole_msecs, (1000 * 1000));
 	decimal_msecs = remainder_ns / 1000;

arch/x86/kernel/paravirt.c

@@ -115,8 +115,18 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 	return 5;
 }
 
-/* Neat trick to map patch type back to the call within the
- * corresponding structure. */
+DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
+
+void __init native_pv_lock_init(void)
+{
+	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+		static_branch_disable(&virt_spin_lock_key);
+}
+
+/*
+ * Neat trick to map patch type back to the call within the
+ * corresponding structure.
+ */
 static void *get_call_destination(u8 type)
 {
 	struct paravirt_patch_template tmpl = {

arch/x86/kernel/smpboot.c

@@ -77,6 +77,7 @@
 #include <asm/i8259.h>
 #include <asm/realmode.h>
 #include <asm/misc.h>
+#include <asm/qspinlock.h>
 
 /* Number of siblings per CPU package */
 int smp_num_siblings = 1;
@@ -1095,7 +1096,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	unsigned long flags;
 	int err, ret = 0;
 
-	WARN_ON(irqs_disabled());
+	lockdep_assert_irqs_enabled();
 
 	pr_debug("++++++++++++++++++++=_---CPU UP  %u\n", cpu);
 
@@ -1358,6 +1359,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
+	native_pv_lock_init();
+
 	uv_system_init();
 
 	set_mtrr_aps_delayed_init();

arch/x86/kvm/mmu.c

@@ -443,7 +443,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 
 static u64 __get_spte_lockless(u64 *sptep)
 {
-	return ACCESS_ONCE(*sptep);
+	return READ_ONCE(*sptep);
 }
 #else
 union split_spte {
@@ -4819,7 +4819,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	 * If we don't have indirect shadow pages, it means no page is
 	 * write-protected, so we can exit simply.
 	 */
-	if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+	if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
 		return;
 
 	remote_flush = local_flush = false;

arch/x86/kvm/page_track.c

@@ -157,7 +157,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
 		return false;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
-	return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
+	return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
 }
 
 void kvm_page_track_cleanup(struct kvm *kvm)

arch/x86/lib/rwsem.S

@@ -98,6 +98,18 @@ ENTRY(call_rwsem_down_read_failed)
 	ret
 ENDPROC(call_rwsem_down_read_failed)
 
+ENTRY(call_rwsem_down_read_failed_killable)
+	FRAME_BEGIN
+	save_common_regs
+	__ASM_SIZE(push,) %__ASM_REG(dx)
+	movq %rax,%rdi
+	call rwsem_down_read_failed_killable
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
+	restore_common_regs
+	FRAME_END
+	ret
+ENDPROC(call_rwsem_down_read_failed_killable)
+
 ENTRY(call_rwsem_down_write_failed)
 	FRAME_BEGIN
 	save_common_regs

arch/x86/mm/extable.c

@@ -67,12 +67,17 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
 	 * wrapped around) will be set. Additionally, seeing the refcount
 	 * reach 0 will set ZF (Zero Flag: result was zero). In each of
 	 * these cases we want a report, since it's a boundary condition.
-	 *
+	 * The SF case is not reported since it indicates post-boundary
+	 * manipulations below zero or above INT_MAX. And if none of the
+	 * flags are set, something has gone very wrong, so report it.
 	 */
 	if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
 		bool zero = regs->flags & X86_EFLAGS_ZF;
 
 		refcount_error_report(regs, zero ? "hit zero" : "overflow");
+	} else if ((regs->flags & X86_EFLAGS_SF) == 0) {
+		/* Report if none of OF, ZF, nor SF are set. */
+		refcount_error_report(regs, "unexpected saturation");
 	}
 
 	return true;

arch/x86/xen/p2m.c

@@ -547,7 +547,7 @@ int xen_alloc_p2m_entry(unsigned long pfn)
 	if (p2m_top_mfn && pfn < MAX_P2M_PFN) {
 		topidx = p2m_top_index(pfn);
 		top_mfn_p = &p2m_top_mfn[topidx];
-		mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]);
+		mid_mfn = READ_ONCE(p2m_top_mfn_p[topidx]);
 
 		BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
 

arch/x86/xen/spinlock.c

@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 #include <asm/paravirt.h>
+#include <asm/qspinlock.h>
 
 #include <xen/interface/xen.h>
 #include <xen/events.h>
@@ -81,8 +82,11 @@ void xen_init_lock_cpu(int cpu)
 	int irq;
 	char *name;
 
-	if (!xen_pvspin)
+	if (!xen_pvspin) {
+		if (cpu == 0)
+			static_branch_disable(&virt_spin_lock_key);
 		return;
+	}
 
 	WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
 	     cpu, per_cpu(lock_kicker_irq, cpu));

arch/xtensa/include/asm/spinlock.h

@@ -33,8 +33,6 @@
 
 #define arch_spin_is_locked(x) ((x)->slock != 0)
 
-#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
@@ -97,8 +95,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
  *  0x80000000  one writer owns the rwlock, no other writers, no readers
  */
 
-#define arch_write_can_lock(x)  ((x)->lock == 0)
-
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
@@ -200,7 +196,4 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 			: "memory");
 }
 
-#define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
-
 #endif	/* _XTENSA_SPINLOCK_H */

arch/xtensa/platforms/xtfpga/lcd.c

@@ -34,23 +34,23 @@
 static void lcd_put_byte(u8 *addr, u8 data)
 {
 #ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS
-	ACCESS_ONCE(*addr) = data;
+	WRITE_ONCE(*addr, data);
 #else
-	ACCESS_ONCE(*addr) = data & 0xf0;
-	ACCESS_ONCE(*addr) = (data << 4) & 0xf0;
+	WRITE_ONCE(*addr, data & 0xf0);
+	WRITE_ONCE(*addr, (data << 4) & 0xf0);
 #endif
 }
 
 static int __init lcd_init(void)
 {
-	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
+	WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT);
 	mdelay(5);
-	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
+	WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT);
 	udelay(200);
-	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
+	WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE8BIT);
 	udelay(50);
 #ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS
-	ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT;
+	WRITE_ONCE(*LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT);
 	udelay(50);
 	lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT);
 	udelay(50);

block/bio.c

@@ -917,17 +917,9 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 }
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
-struct submit_bio_ret {
-	struct completion event;
-	int error;
-};
-
 static void submit_bio_wait_endio(struct bio *bio)
 {
-	struct submit_bio_ret *ret = bio->bi_private;
-
-	ret->error = blk_status_to_errno(bio->bi_status);
-	complete(&ret->event);
+	complete(bio->bi_private);
 }
 
 /**
@@ -943,16 +935,15 @@ static void submit_bio_wait_endio(struct bio *bio)
  */
 int submit_bio_wait(struct bio *bio)
 {
-	struct submit_bio_ret ret;
+	DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map);
 
-	init_completion(&ret.event);
-	bio->bi_private = &ret;
+	bio->bi_private = &done;
 	bio->bi_end_io = submit_bio_wait_endio;
 	bio->bi_opf |= REQ_SYNC;
 	submit_bio(bio);
-	wait_for_completion_io(&ret.event);
+	wait_for_completion_io(&done);
 
-	return ret.error;
+	return blk_status_to_errno(bio->bi_status);
 }
 EXPORT_SYMBOL(submit_bio_wait);
 

block/blk-wbt.c

@@ -261,7 +261,7 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
 {
-	u64 now, issue = ACCESS_ONCE(rwb->sync_issue);
+	u64 now, issue = READ_ONCE(rwb->sync_issue);
 
 	if (!issue || !rwb->sync_cookie)
 		return 0;

block/genhd.c

@@ -1354,13 +1354,7 @@ dev_t blk_lookup_devt(const char *name, int partno)
 }
 EXPORT_SYMBOL(blk_lookup_devt);
 
-struct gendisk *alloc_disk(int minors)
-{
-	return alloc_disk_node(minors, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_disk);
-
-struct gendisk *alloc_disk_node(int minors, int node_id)
+struct gendisk *__alloc_disk_node(int minors, int node_id)
 {
 	struct gendisk *disk;
 	struct disk_part_tbl *ptbl;
@@ -1411,7 +1405,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 	}
 	return disk;
 }
-EXPORT_SYMBOL(alloc_disk_node);
+EXPORT_SYMBOL(__alloc_disk_node);
 
 struct kobject *get_disk(struct gendisk *disk)
 {

drivers/base/core.c

@@ -668,7 +668,7 @@ const char *dev_driver_string(const struct device *dev)
 	 * so be careful about accessing it.  dev->bus and dev->class should
 	 * never change once they are set, so they don't need special care.
 	 */
-	drv = ACCESS_ONCE(dev->driver);
+	drv = READ_ONCE(dev->driver);
 	return drv ? drv->name :
 			(dev->bus ? dev->bus->name :
 			(dev->class ? dev->class->name : ""));

drivers/base/power/runtime.c

@@ -134,11 +134,11 @@ unsigned long pm_runtime_autosuspend_expiration(struct device *dev)
 	if (!dev->power.use_autosuspend)
 		goto out;
 
-	autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay);
+	autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay);
 	if (autosuspend_delay < 0)
 		goto out;
 
-	last_busy = ACCESS_ONCE(dev->power.last_busy);
+	last_busy = READ_ONCE(dev->power.last_busy);
 	elapsed = jiffies - last_busy;
 	if (elapsed < 0)
 		goto out;	/* jiffies has wrapped around. */

drivers/char/random.c

@@ -641,7 +641,7 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
 		return;
 
 retry:
-	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
+	entropy_count = orig = READ_ONCE(r->entropy_count);
 	if (nfrac < 0) {
 		/* Debit */
 		entropy_count += nfrac;
@@ -1265,7 +1265,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 
 	/* Can we pull enough? */
 retry:
-	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
+	entropy_count = orig = READ_ONCE(r->entropy_count);
 	ibytes = nbytes;
 	/* never pull more than available */
 	have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);

drivers/clocksource/bcm2835_timer.c

@@ -71,7 +71,7 @@ static irqreturn_t bcm2835_time_interrupt(int irq, void *dev_id)
 	if (readl_relaxed(timer->control) & timer->match_mask) {
 		writel_relaxed(timer->match_mask, timer->control);
 
-		event_handler = ACCESS_ONCE(timer->evt.event_handler);
+		event_handler = READ_ONCE(timer->evt.event_handler);
 		if (event_handler)
 			event_handler(&timer->evt);
 		return IRQ_HANDLED;

drivers/crypto/caam/jr.c

@@ -172,7 +172,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 
 	while (rd_reg32(&jrp->rregs->outring_used)) {
 
-		head = ACCESS_ONCE(jrp->head);
+		head = READ_ONCE(jrp->head);
 
 		spin_lock(&jrp->outlock);
 
@@ -341,7 +341,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	spin_lock_bh(&jrp->inplock);
 
 	head = jrp->head;
-	tail = ACCESS_ONCE(jrp->tail);
+	tail = READ_ONCE(jrp->tail);
 
 	if (!rd_reg32(&jrp->rregs->inpring_avail) ||
 	    CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) {

drivers/crypto/nx/nx-842-powernv.c

@@ -193,7 +193,7 @@ static int wait_for_csb(struct nx842_workmem *wmem,
 	ktime_t start = wmem->start, now = ktime_get();
 	ktime_t timeout = ktime_add_ms(start, CSB_WAIT_MAX);
 
-	while (!(ACCESS_ONCE(csb->flags) & CSB_V)) {
+	while (!(READ_ONCE(csb->flags) & CSB_V)) {
 		cpu_relax();
 		now = ktime_get();
 		if (ktime_after(now, timeout))

drivers/edac/altera_edac.c

@@ -175,11 +175,11 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
 	/*
 	 * To trigger the error, we need to read the data back
 	 * (the data was written with errors above).
-	 * The ACCESS_ONCE macros and printk are used to prevent the
+	 * The READ_ONCE macros and printk are used to prevent the
 	 * the compiler optimizing these reads out.
 	 */
-	reg = ACCESS_ONCE(ptemp[0]);
-	read_reg = ACCESS_ONCE(ptemp[1]);
+	reg = READ_ONCE(ptemp[0]);
+	read_reg = READ_ONCE(ptemp[1]);
 	/* Force Read */
 	rmb();
 
@@ -618,7 +618,7 @@ static ssize_t altr_edac_device_trig(struct file *file,
 	for (i = 0; i < (priv->trig_alloc_sz / sizeof(*ptemp)); i++) {
 		/* Read data so we're in the correct state */
 		rmb();
-		if (ACCESS_ONCE(ptemp[i]))
+		if (READ_ONCE(ptemp[i]))
 			result = -1;
 		/* Toggle Error bit (it is latched), leave ECC enabled */
 		writel(error_mask, (drvdata->base + priv->set_err_ofst));
@@ -635,7 +635,7 @@ static ssize_t altr_edac_device_trig(struct file *file,
 
 	/* Read out written data. ECC error caused here */
 	for (i = 0; i < ALTR_TRIGGER_READ_WRD_CNT; i++)
-		if (ACCESS_ONCE(ptemp[i]) != i)
+		if (READ_ONCE(ptemp[i]) != i)
 			edac_printk(KERN_ERR, EDAC_DEVICE,
 				    "Read doesn't match written data\n");
 

drivers/firewire/ohci.c

@@ -734,7 +734,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx,
 	__le16 res_count, next_res_count;
 
 	i = ar_first_buffer_index(ctx);
-	res_count = ACCESS_ONCE(ctx->descriptors[i].res_count);
+	res_count = READ_ONCE(ctx->descriptors[i].res_count);
 
 	/* A buffer that is not yet completely filled must be the last one. */
 	while (i != last && res_count == 0) {
@@ -742,8 +742,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx,
 		/* Peek at the next descriptor. */
 		next_i = ar_next_buffer_index(i);
 		rmb(); /* read descriptors in order */
-		next_res_count = ACCESS_ONCE(
-				ctx->descriptors[next_i].res_count);
+		next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count);
 		/*
 		 * If the next descriptor is still empty, we must stop at this
 		 * descriptor.
@@ -759,8 +758,7 @@ static unsigned int ar_search_last_active_buffer(struct ar_context *ctx,
 			if (MAX_AR_PACKET_SIZE > PAGE_SIZE && i != last) {
 				next_i = ar_next_buffer_index(next_i);
 				rmb();
-				next_res_count = ACCESS_ONCE(
-					ctx->descriptors[next_i].res_count);
+				next_res_count = READ_ONCE(ctx->descriptors[next_i].res_count);
 				if (next_res_count != cpu_to_le16(PAGE_SIZE))
 					goto next_buffer_is_active;
 			}
@@ -2812,7 +2810,7 @@ static int handle_ir_buffer_fill(struct context *context,
 	u32 buffer_dma;
 
 	req_count = le16_to_cpu(last->req_count);
-	res_count = le16_to_cpu(ACCESS_ONCE(last->res_count));
+	res_count = le16_to_cpu(READ_ONCE(last->res_count));
 	completed = req_count - res_count;
 	buffer_dma = le32_to_cpu(last->data_address);
 

drivers/firmware/tegra/ivc.c

@@ -99,11 +99,11 @@ static inline bool tegra_ivc_empty(struct tegra_ivc *ivc,
 {
 	/*
 	 * This function performs multiple checks on the same values with
-	 * security implications, so create snapshots with ACCESS_ONCE() to
+	 * security implications, so create snapshots with READ_ONCE() to
 	 * ensure that these checks use the same values.
 	 */
-	u32 tx = ACCESS_ONCE(header->tx.count);
-	u32 rx = ACCESS_ONCE(header->rx.count);
+	u32 tx = READ_ONCE(header->tx.count);
+	u32 rx = READ_ONCE(header->rx.count);
 
 	/*
 	 * Perform an over-full check to prevent denial of service attacks
@@ -124,8 +124,8 @@ static inline bool tegra_ivc_empty(struct tegra_ivc *ivc,
 static inline bool tegra_ivc_full(struct tegra_ivc *ivc,
 				  struct tegra_ivc_header *header)
 {
-	u32 tx = ACCESS_ONCE(header->tx.count);
-	u32 rx = ACCESS_ONCE(header->rx.count);
+	u32 tx = READ_ONCE(header->tx.count);
+	u32 rx = READ_ONCE(header->rx.count);
 
 	/*
 	 * Invalid cases where the counters indicate that the queue is over
@@ -137,8 +137,8 @@ static inline bool tegra_ivc_full(struct tegra_ivc *ivc,
 static inline u32 tegra_ivc_available(struct tegra_ivc *ivc,
 				      struct tegra_ivc_header *header)
 {
-	u32 tx = ACCESS_ONCE(header->tx.count);
-	u32 rx = ACCESS_ONCE(header->rx.count);
+	u32 tx = READ_ONCE(header->tx.count);
+	u32 rx = READ_ONCE(header->rx.count);
 
 	/*
 	 * This function isn't expected to be used in scenarios where an
@@ -151,8 +151,8 @@ static inline u32 tegra_ivc_available(struct tegra_ivc *ivc,
 
 static inline void tegra_ivc_advance_tx(struct tegra_ivc *ivc)
 {
-	ACCESS_ONCE(ivc->tx.channel->tx.count) =
-		ACCESS_ONCE(ivc->tx.channel->tx.count) + 1;
+	WRITE_ONCE(ivc->tx.channel->tx.count,
+		   READ_ONCE(ivc->tx.channel->tx.count) + 1);
 
 	if (ivc->tx.position == ivc->num_frames - 1)
 		ivc->tx.position = 0;
@@ -162,8 +162,8 @@ static inline void tegra_ivc_advance_tx(struct tegra_ivc *ivc)
 
 static inline void tegra_ivc_advance_rx(struct tegra_ivc *ivc)
 {
-	ACCESS_ONCE(ivc->rx.channel->rx.count) =
-		ACCESS_ONCE(ivc->rx.channel->rx.count) + 1;
+	WRITE_ONCE(ivc->rx.channel->rx.count,
+		   READ_ONCE(ivc->rx.channel->rx.count) + 1);
 
 	if (ivc->rx.position == ivc->num_frames - 1)
 		ivc->rx.position = 0;
@@ -428,7 +428,7 @@ int tegra_ivc_notified(struct tegra_ivc *ivc)
 
 	/* Copy the receiver's state out of shared memory. */
 	tegra_ivc_invalidate(ivc, ivc->rx.phys + offset);
-	state = ACCESS_ONCE(ivc->rx.channel->tx.state);
+	state = READ_ONCE(ivc->rx.channel->tx.state);
 
 	if (state == TEGRA_IVC_STATE_SYNC) {
 		offset = offsetof(struct tegra_ivc_header, tx.count);

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -260,7 +260,7 @@ static void amdgpu_fence_fallback(unsigned long arg)
  */
 int amdgpu_fence_wait_empty(struct amdgpu_ring *ring)
 {
-	uint64_t seq = ACCESS_ONCE(ring->fence_drv.sync_seq);
+	uint64_t seq = READ_ONCE(ring->fence_drv.sync_seq);
 	struct dma_fence *fence, **ptr;
 	int r;
 
@@ -300,7 +300,7 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring)
 	amdgpu_fence_process(ring);
 	emitted = 0x100000000ull;
 	emitted -= atomic_read(&ring->fence_drv.last_seq);
-	emitted += ACCESS_ONCE(ring->fence_drv.sync_seq);
+	emitted += READ_ONCE(ring->fence_drv.sync_seq);
 	return lower_32_bits(emitted);
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -788,11 +788,11 @@ static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data)
 	seq_printf(m, "\t0x%08x: %12ld byte %s",
 		   id, amdgpu_bo_size(bo), placement);
 
-	offset = ACCESS_ONCE(bo->tbo.mem.start);
+	offset = READ_ONCE(bo->tbo.mem.start);
 	if (offset != AMDGPU_BO_INVALID_OFFSET)
 		seq_printf(m, " @ 0x%010Lx", offset);
 
-	pin_count = ACCESS_ONCE(bo->pin_count);
+	pin_count = READ_ONCE(bo->pin_count);
 	if (pin_count)
 		seq_printf(m, " pin count %d", pin_count);
 	seq_printf(m, "\n");

drivers/gpu/drm/amd/scheduler/gpu_scheduler.c

@@ -187,7 +187,7 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
 	if (kfifo_is_empty(&entity->job_queue))
 		return false;
 
-	if (ACCESS_ONCE(entity->dependency))
+	if (READ_ONCE(entity->dependency))
 		return false;
 
 	return true;

drivers/gpu/drm/radeon/radeon_gem.c

@@ -451,7 +451,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 	else
 		r = 0;
 
-	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
+	cur_placement = READ_ONCE(robj->tbo.mem.mem_type);
 	args->domain = radeon_mem_type_to_domain(cur_placement);
 	drm_gem_object_put_unlocked(gobj);
 	return r;
@@ -481,7 +481,7 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 		r = ret;
 
 	/* Flush HDP cache via MMIO if necessary */
-	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
+	cur_placement = READ_ONCE(robj->tbo.mem.mem_type);
 	if (rdev->asic->mmio_hdp_flush &&
 	    radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM)
 		robj->rdev->asic->mmio_hdp_flush(rdev);

drivers/gpu/drm/vmwgfx/vmwgfx_surface.c

@@ -904,7 +904,7 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 		if (unlikely(drm_is_render_client(file_priv)))
 			require_exist = true;
 
-		if (ACCESS_ONCE(vmw_fpriv(file_priv)->locked_master)) {
+		if (READ_ONCE(vmw_fpriv(file_priv)->locked_master)) {
 			DRM_ERROR("Locked master refused legacy "
 				  "surface reference.\n");
 			return -EACCES;

drivers/infiniband/hw/hfi1/file_ops.c

@@ -380,7 +380,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
 		if (sc->flags & SCF_FROZEN) {
 			wait_event_interruptible_timeout(
 				dd->event_queue,
-				!(ACCESS_ONCE(dd->flags) & HFI1_FROZEN),
+				!(READ_ONCE(dd->flags) & HFI1_FROZEN),
 				msecs_to_jiffies(SEND_CTXT_HALT_TIMEOUT));
 			if (dd->flags & HFI1_FROZEN)
 				return -ENOLCK;

drivers/infiniband/hw/hfi1/pio.c

@@ -1423,14 +1423,14 @@ retry:
 			goto done;
 		}
 		/* copy from receiver cache line and recalculate */
-		sc->alloc_free = ACCESS_ONCE(sc->free);
+		sc->alloc_free = READ_ONCE(sc->free);
 		avail =
 			(unsigned long)sc->credits -
 			(sc->fill - sc->alloc_free);
 		if (blocks > avail) {
 			/* still no room, actively update */
 			sc_release_update(sc);
-			sc->alloc_free = ACCESS_ONCE(sc->free);
+			sc->alloc_free = READ_ONCE(sc->free);
 			trycount++;
 			goto retry;
 		}
@@ -1667,7 +1667,7 @@ void sc_release_update(struct send_context *sc)
 
 	/* call sent buffer callbacks */
 	code = -1;				/* code not yet set */
-	head = ACCESS_ONCE(sc->sr_head);	/* snapshot the head */
+	head = READ_ONCE(sc->sr_head);	/* snapshot the head */
 	tail = sc->sr_tail;
 	while (head != tail) {
 		pbuf = &sc->sr[tail].pbuf;

drivers/infiniband/hw/hfi1/ruc.c

@@ -363,7 +363,7 @@ static void ruc_loopback(struct rvt_qp *sqp)
 
 again:
 	smp_read_barrier_depends(); /* see post_one_send() */
-	if (sqp->s_last == ACCESS_ONCE(sqp->s_head))
+	if (sqp->s_last == READ_ONCE(sqp->s_head))
 		goto clr_busy;
 	wqe = rvt_get_swqe_ptr(sqp, sqp->s_last);
 

drivers/infiniband/hw/hfi1/sdma.c

@@ -1725,7 +1725,7 @@ retry:
 
 		swhead = sde->descq_head & sde->sdma_mask;
 		/* this code is really bad for cache line trading */
-		swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask;
+		swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask;
 		cnt = sde->descq_cnt;
 
 		if (swhead < swtail)
@@ -1872,7 +1872,7 @@ retry:
 	if ((status & sde->idle_mask) && !idle_check_done) {
 		u16 swtail;
 
-		swtail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask;
+		swtail = READ_ONCE(sde->descq_tail) & sde->sdma_mask;
 		if (swtail != hwhead) {
 			hwhead = (u16)read_sde_csr(sde, SD(HEAD));
 			idle_check_done = 1;
@@ -2222,7 +2222,7 @@ void sdma_seqfile_dump_sde(struct seq_file *s, struct sdma_engine *sde)
 	u16 len;
 
 	head = sde->descq_head & sde->sdma_mask;
-	tail = ACCESS_ONCE(sde->descq_tail) & sde->sdma_mask;
+	tail = READ_ONCE(sde->descq_tail) & sde->sdma_mask;
 	seq_printf(s, SDE_FMT, sde->this_idx,
 		   sde->cpu,
 		   sdma_state_name(sde->state.current_state),
@@ -3305,7 +3305,7 @@ int sdma_ahg_alloc(struct sdma_engine *sde)
 		return -EINVAL;
 	}
 	while (1) {
-		nr = ffz(ACCESS_ONCE(sde->ahg_bits));
+		nr = ffz(READ_ONCE(sde->ahg_bits));
 		if (nr > 31) {
 			trace_hfi1_ahg_allocate(sde, -ENOSPC);
 			return -ENOSPC;

drivers/infiniband/hw/hfi1/sdma.h

@@ -445,7 +445,7 @@ static inline u16 sdma_descq_freecnt(struct sdma_engine *sde)
 {
 	return sde->descq_cnt -
 		(sde->descq_tail -
-		 ACCESS_ONCE(sde->descq_head)) - 1;
+		 READ_ONCE(sde->descq_head)) - 1;
 }
 
 static inline u16 sdma_descq_inprocess(struct sdma_engine *sde)

drivers/infiniband/hw/hfi1/uc.c

@@ -80,7 +80,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 			goto bail;
 		/* We are in the error state, flush the work request. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_last == ACCESS_ONCE(qp->s_head))
+		if (qp->s_last == READ_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (iowait_sdma_pending(&priv->s_iowait)) {
@@ -121,7 +121,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 			goto bail;
 		/* Check if send work queue is empty. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_cur == ACCESS_ONCE(qp->s_head)) {
+		if (qp->s_cur == READ_ONCE(qp->s_head)) {
 			clear_ahg(qp);
 			goto bail;
 		}

drivers/infiniband/hw/hfi1/ud.c

@@ -487,7 +487,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 			goto bail;
 		/* We are in the error state, flush the work request. */
 		smp_read_barrier_depends(); /* see post_one_send */
-		if (qp->s_last == ACCESS_ONCE(qp->s_head))
+		if (qp->s_last == READ_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (iowait_sdma_pending(&priv->s_iowait)) {
@@ -501,7 +501,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	/* see post_one_send() */
 	smp_read_barrier_depends();
-	if (qp->s_cur == ACCESS_ONCE(qp->s_head))
+	if (qp->s_cur == READ_ONCE(qp->s_head))
 		goto bail;
 
 	wqe = rvt_get_swqe_ptr(qp, qp->s_cur);

drivers/infiniband/hw/hfi1/user_sdma.c

@@ -276,7 +276,7 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
 		/* Wait until all requests have been freed. */
 		wait_event_interruptible(
 			pq->wait,
-			(ACCESS_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE));
+			(READ_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE));
 		kfree(pq->reqs);
 		kfree(pq->req_in_use);
 		kmem_cache_destroy(pq->txreq_cache);
@@ -591,7 +591,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 			if (ret != -EBUSY) {
 				req->status = ret;
 				WRITE_ONCE(req->has_error, 1);
-				if (ACCESS_ONCE(req->seqcomp) ==
+				if (READ_ONCE(req->seqcomp) ==
 				    req->seqsubmitted - 1)
 					goto free_req;
 				return ret;
@@ -825,7 +825,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts)
 		 */
 		if (req->data_len) {
 			iovec = &req->iovs[req->iov_idx];
-			if (ACCESS_ONCE(iovec->offset) == iovec->iov.iov_len) {
+			if (READ_ONCE(iovec->offset) == iovec->iov.iov_len) {
 				if (++req->iov_idx == req->data_iovs) {
 					ret = -EFAULT;
 					goto free_txreq;
@@ -1390,7 +1390,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status)
 	} else {
 		if (status != SDMA_TXREQ_S_OK)
 			req->status = status;
-		if (req->seqcomp == (ACCESS_ONCE(req->seqsubmitted) - 1) &&
+		if (req->seqcomp == (READ_ONCE(req->seqsubmitted) - 1) &&
 		    (READ_ONCE(req->done) ||
 		     READ_ONCE(req->has_error))) {
 			user_sdma_free_request(req, false);

drivers/infiniband/hw/qib/qib_ruc.c

@@ -368,7 +368,7 @@ static void qib_ruc_loopback(struct rvt_qp *sqp)
 
 again:
 	smp_read_barrier_depends(); /* see post_one_send() */
-	if (sqp->s_last == ACCESS_ONCE(sqp->s_head))
+	if (sqp->s_last == READ_ONCE(sqp->s_head))
 		goto clr_busy;
 	wqe = rvt_get_swqe_ptr(sqp, sqp->s_last);
 

drivers/infiniband/hw/qib/qib_uc.c

@@ -61,7 +61,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags)
 			goto bail;
 		/* We are in the error state, flush the work request. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_last == ACCESS_ONCE(qp->s_head))
+		if (qp->s_last == READ_ONCE(qp->s_head))
 			goto bail;
 		/* If DMAs are in progress, we can't flush immediately. */
 		if (atomic_read(&priv->s_dma_busy)) {
@@ -91,7 +91,7 @@ int qib_make_uc_req(struct rvt_qp *qp, unsigned long *flags)
 			goto bail;
 		/* Check if send work queue is empty. */
 		smp_read_barrier_depends(); /* see post_one_send() */
-		if (qp->s_cur == ACCESS_ONCE(qp->s_head))
+		if (qp->s_cur == READ_ONCE(qp->s_head))
 			goto bail;
 		/*
 		 * Start a new request.