locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()

Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.

For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.

However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:

----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()

// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch

virtual patch

@ depends on patch @
expression E1, E2;
@@

- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)

@ depends on patch @
expression E;
@@

- ACCESS_ONCE(E)
+ READ_ONCE(E)
----

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/arc/kernel/smp.c

@@ -245,7 +245,7 @@ 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/spinlock.h

@@ -71,7 +71,7 @@ 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();

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/ia64/include/asm/spinlock.h

@@ -61,7 +61,7 @@ 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;
@@ -73,19 +73,19 @@ 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;
 }

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/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

@@ -260,7 +260,7 @@ 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/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

@@ -117,14 +117,14 @@ extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
 static inline int arch_read_trylock_once(arch_rwlock_t *rw)
 {
-	int old = ACCESS_ONCE(rw->lock);
+	int old = READ_ONCE(rw->lock);
 	return likely(old >= 0 &&
 		      __atomic_cmpxchg_bool(&rw->lock, old, old + 1));
 }
 
 static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 {
-	int old = ACCESS_ONCE(rw->lock);
+	int old = READ_ONCE(rw->lock);
 	return likely(old == 0 &&
 		      __atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000));
 }
@@ -211,7 +211,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	int old;
 
 	do {
-		old = ACCESS_ONCE(rw->lock);
+		old = READ_ONCE(rw->lock);
 	} while (!__atomic_cmpxchg_bool(&rw->lock, old, old - 1));
 }
 

arch/s390/lib/spinlock.c

@@ -162,8 +162,8 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
-		old = ACCESS_ONCE(rw->lock);
-		owner = ACCESS_ONCE(rw->owner);
+		old = READ_ONCE(rw->lock);
+		owner = READ_ONCE(rw->owner);
 		if (old < 0)
 			continue;
 		if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1))
@@ -178,7 +178,7 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw)
 	int old;
 
 	while (count-- > 0) {
-		old = ACCESS_ONCE(rw->lock);
+		old = READ_ONCE(rw->lock);
 		if (old < 0)
 			continue;
 		if (__atomic_cmpxchg_bool(&rw->lock, old, old + 1))
@@ -202,8 +202,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, int prev)
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
-		old = ACCESS_ONCE(rw->lock);
-		owner = ACCESS_ONCE(rw->owner);
+		old = READ_ONCE(rw->lock);
+		owner = READ_ONCE(rw->owner);
 		smp_mb();
 		if (old >= 0) {
 			prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
@@ -230,8 +230,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
-		old = ACCESS_ONCE(rw->lock);
-		owner = ACCESS_ONCE(rw->owner);
+		old = READ_ONCE(rw->lock);
+		owner = READ_ONCE(rw->owner);
 		if (old >= 0 &&
 		    __atomic_cmpxchg_bool(&rw->lock, old, old | 0x80000000))
 			prev = old;
@@ -251,7 +251,7 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw)
 	int old;
 
 	while (count-- > 0) {
-		old = ACCESS_ONCE(rw->lock);
+		old = READ_ONCE(rw->lock);
 		if (old)
 			continue;
 		if (__atomic_cmpxchg_bool(&rw->lock, 0, 0x80000000))

arch/sparc/include/asm/atomic_32.h

@@ -31,7 +31,7 @@ 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/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/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/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;

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;

arch/x86/include/asm/vgtod.h

@@ -48,7 +48,7 @@ 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;