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
  ...

90 files changed, 229 insertions, 230 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 12ebd055724c..4b8ba2a75a4d 100644
--- a/drivers/base/core.c
+++ b/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 : ""));
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 7bcf80fa9ada..41d7c2b99f69 100644
--- a/drivers/base/power/runtime.c
+++ b/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. */
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 8ad92707e45f..6c7ccac2679e 100644
--- a/drivers/char/random.c
+++ b/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);
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 39e489a96ad7..60da2537bef9 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/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;
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index d258953ff488..f4f258075b89 100644
--- a/drivers/crypto/caam/jr.c
+++ b/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) {
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
index 874ddf5e9087..0f20f5ec9617 100644
--- a/drivers/crypto/nx/nx-842-powernv.c
+++ b/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))
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 346c4987b284..11d6419788c2 100644
--- a/drivers/edac/altera_edac.c
+++ b/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");
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 8bf89267dc25..ccf52368a073 100644
--- a/drivers/firewire/ohci.c
+++ b/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);
 
diff --git a/drivers/firmware/tegra/ivc.c b/drivers/firmware/tegra/ivc.c
index a01461d63f68..00de793e6423 100644
--- a/drivers/firmware/tegra/ivc.c
+++ b/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);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 333bad749067..303b5e099a98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/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);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_g