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

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

   - Implement wraparound-safe refcount_t and kref_t types based on
     generic atomic primitives (Peter Zijlstra)

   - Improve and fix the ww_mutex code (Nicolai Hähnle)

   - Add self-tests to the ww_mutex code (Chris Wilson)

   - Optimize percpu-rwsems with the 'rcuwait' mechanism (Davidlohr
     Bueso)

   - Micro-optimize the current-task logic all around the core kernel
     (Davidlohr Bueso)

   - Tidy up after recent optimizations: remove stale code and APIs,
     clean up the code (Waiman Long)

   - ... plus misc fixes, updates and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  fork: Fix task_struct alignment
  locking/spinlock/debug: Remove spinlock lockup detection code
  lockdep: Fix incorrect condition to print bug msgs for MAX_LOCKDEP_CHAIN_HLOCKS
  lkdtm: Convert to refcount_t testing
  kref: Implement 'struct kref' using refcount_t
  refcount_t: Introduce a special purpose refcount type
  sched/wake_q: Clarify queue reinit comment
  sched/wait, rcuwait: Fix typo in comment
  locking/mutex: Fix lockdep_assert_held() fail
  locking/rtmutex: Flip unlikely() branch to likely() in __rt_mutex_slowlock()
  locking/rwsem: Reinit wake_q after use
  locking/rwsem: Remove unnecessary atomic_long_t casts
  jump_labels: Move header guard #endif down where it belongs
  locking/atomic, kref: Implement kref_put_lock()
  locking/ww_mutex: Turn off __must_check for now
  locking/atomic, kref: Avoid more abuse
  locking/atomic, kref: Use kref_get_unless_zero() more
  locking/atomic, kref: Kill kref_sub()
  locking/atomic, kref: Add kref_read()
  locking/atomic, kref: Add KREF_INIT()
  ...

Documentation/locking/ww-mutex-design.txt

@@ -309,11 +309,15 @@ Design:
   normal mutex locks, which are far more common. As such there is only a small
   increase in code size if wait/wound mutexes are not used.
 
+  We maintain the following invariants for the wait list:
+  (1) Waiters with an acquire context are sorted by stamp order; waiters
+      without an acquire context are interspersed in FIFO order.
+  (2) Among waiters with contexts, only the first one can have other locks
+      acquired already (ctx->acquired > 0). Note that this waiter may come
+      after other waiters without contexts in the list.
+
   In general, not much contention is expected. The locks are typically used to
-  serialize access to resources for devices. The only way to make wakeups
-  smarter would be at the cost of adding a field to struct mutex_waiter. This
-  would add overhead to all cases where normal mutexes are used, and
-  ww_mutexes are generally less performance sensitive.
+  serialize access to resources for devices.
 
 Lockdep:
   Special care has been taken to warn for as many cases of api abuse

arch/um/drivers/random.c

@@ -76,7 +76,7 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size,
 			add_sigio_fd(random_fd);
 
 			add_wait_queue(&host_read_wait, &wait);
-			set_task_state(current, TASK_INTERRUPTIBLE);
+			set_current_state(TASK_INTERRUPTIBLE);
 
 			schedule();
 			remove_wait_queue(&host_read_wait, &wait);

arch/x86/include/asm/spinlock.h

@@ -23,9 +23,6 @@
 /* How long a lock should spin before we consider blocking */
 #define SPIN_THRESHOLD	(1 << 15)
 
-extern struct static_key paravirt_ticketlocks_enabled;
-static __always_inline bool static_key_false(struct static_key *key);
-
 #include <asm/qspinlock.h>
 
 /*

arch/x86/kernel/jump_label.c

@@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line)
 	 * Something went wrong. Crash the box, as something could be
 	 * corrupting the kernel.
 	 */
-	pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n",
-	       ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line);
+	pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line);
 	BUG();
 }
 

arch/x86/kernel/kvm.c

@@ -620,18 +620,4 @@ void __init kvm_spinlock_init(void)
 	}
 }
 
-static __init int kvm_spinlock_init_jump(void)
-{
-	if (!kvm_para_available())
-		return 0;
-	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
-		return 0;
-
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
-
-	return 0;
-}
-early_initcall(kvm_spinlock_init_jump);
-
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */

arch/x86/kernel/paravirt-spinlocks.c

@@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = {
 #endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
-
-struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE;
-EXPORT_SYMBOL(paravirt_ticketlocks_enabled);

arch/x86/xen/spinlock.c

@@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void)
 	pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
 }
 
-/*
- * While the jump_label init code needs to happend _after_ the jump labels are
- * enabled and before SMP is started. Hence we use pre-SMP initcall level
- * init. We cannot do it in xen_init_spinlocks as that is done before
- * jump labels are activated.
- */
-static __init int xen_init_spinlocks_jump(void)
-{
-	if (!xen_pvspin)
-		return 0;
-
-	if (!xen_domain())
-		return 0;
-
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-	return 0;
-}
-early_initcall(xen_init_spinlocks_jump);
-
 static __init int xen_parse_nopvspin(char *arg)
 {
 	xen_pvspin = false;

drivers/block/drbd/drbd_bitmap.c

@@ -1070,7 +1070,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 		.done = 0,
 		.flags = flags,
 		.error = 0,
-		.kref = { ATOMIC_INIT(2) },
+		.kref = KREF_INIT(2),
 	};
 
 	if (!get_ldev_if_state(device, D_ATTACHING)) {  /* put is in drbd_bm_aio_ctx_destroy() */

drivers/block/drbd/drbd_main.c

@@ -2948,7 +2948,6 @@ void drbd_delete_device(struct drbd_device *device)
 	struct drbd_resource *resource = device->resource;
 	struct drbd_connection *connection;
 	struct drbd_peer_device *peer_device;
-	int refs = 3;
 
 	/* move to free_peer_device() */
 	for_each_peer_device(peer_device, device)
@@ -2956,13 +2955,15 @@ void drbd_delete_device(struct drbd_device *device)
 	drbd_debugfs_device_cleanup(device);
 	for_each_connection(connection, resource) {
 		idr_remove(&connection->peer_devices, device->vnr);
-		refs++;
+		kref_put(&device->kref, drbd_destroy_device);
 	}
 	idr_remove(&resource->devices, device->vnr);
+	kref_put(&device->kref, drbd_destroy_device);
 	idr_remove(&drbd_devices, device_to_minor(device));
+	kref_put(&device->kref, drbd_destroy_device);
 	del_gendisk(device->vdisk);
 	synchronize_rcu();
-	kref_sub(&device->kref, refs, drbd_destroy_device);
+	kref_put(&device->kref, drbd_destroy_device);
 }
 
 static int __init drbd_init(void)

drivers/block/drbd/drbd_req.c

@@ -421,7 +421,6 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 	struct drbd_peer_device *peer_device = first_peer_device(device);
 	unsigned s = req->rq_state;
 	int c_put = 0;
-	int k_put = 0;
 
 	if (drbd_suspended(device) && !((s | clear) & RQ_COMPLETION_SUSP))
 		set |= RQ_COMPLETION_SUSP;
@@ -437,6 +436,8 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	/* intent: get references */
 
+	kref_get(&req->kref);
+
 	if (!(s & RQ_LOCAL_PENDING) && (set & RQ_LOCAL_PENDING))
 		atomic_inc(&req->completion_ref);
 
@@ -473,15 +474,12 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	if (!(s & RQ_LOCAL_ABORTED) && (set & RQ_LOCAL_ABORTED)) {
 		D_ASSERT(device, req->rq_state & RQ_LOCAL_PENDING);
-		/* local completion may still come in later,
-		 * we need to keep the req object around. */
-		kref_get(&req->kref);
 		++c_put;
 	}
 
 	if ((s & RQ_LOCAL_PENDING) && (clear & RQ_LOCAL_PENDING)) {
 		if (req->rq_state & RQ_LOCAL_ABORTED)
-			++k_put;
+			kref_put(&req->kref, drbd_req_destroy);
 		else
 			++c_put;
 		list_del_init(&req->req_pending_local);
@@ -503,7 +501,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 		if (s & RQ_NET_SENT)
 			atomic_sub(req->i.size >> 9, &device->ap_in_flight);
 		if (s & RQ_EXP_BARR_ACK)
-			++k_put;
+			kref_put(&req->kref, drbd_req_destroy);
 		req->net_done_jif = jiffies;
 
 		/* in ahead/behind mode, or just in case,
@@ -516,25 +514,16 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	/* potentially complete and destroy */
 
-	if (k_put || c_put) {
-		/* Completion does it's own kref_put.  If we are going to
-		 * kref_sub below, we need req to be still around then. */
-		int at_least = k_put + !!c_put;
-		int refcount = atomic_read(&req->kref.refcount);
-		if (refcount < at_least)
-			drbd_err(device,
-				"mod_rq_state: Logic BUG: %x -> %x: refcount = %d, should be >= %d\n",
-				s, req->rq_state, refcount, at_least);
-	}
-
 	/* If we made progress, retry conflicting peer requests, if any. */
 	if (req->i.waiting)
 		wake_up(&device->misc_wait);
 
-	if (c_put)
-		k_put += drbd_req_put_completion_ref(req, m, c_put);
-	if (k_put)
-		kref_sub(&req->kref, k_put, drbd_req_destroy);
+	if (c_put) {
+		if (drbd_req_put_completion_ref(req, m, c_put))
+			kref_put(&req->kref, drbd_req_destroy);
+	} else {
+		kref_put(&req->kref, drbd_req_destroy);
+	}
 }
 
 static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req)

drivers/block/rbd.c

@@ -1535,7 +1535,7 @@ static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
-		atomic_read(&obj_request->kref.refcount));
+		kref_read(&obj_request->kref));
 	kref_get(&obj_request->kref);
 }
 
@@ -1544,14 +1544,14 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 {
 	rbd_assert(obj_request != NULL);
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
-		atomic_read(&obj_request->kref.refcount));
+		kref_read(&obj_request->kref));
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
 static void rbd_img_request_get(struct rbd_img_request *img_request)
 {
 	dout("%s: img %p (was %d)\n", __func__, img_request,
-	     atomic_read(&img_request->kref.refcount));
+	     kref_read(&img_request->kref));
 	kref_get(&img_request->kref);
 }
 
@@ -1562,7 +1562,7 @@ static void rbd_img_request_put(struct rbd_img_request *img_request)
 {
 	rbd_assert(img_request != NULL);
 	dout("%s: img %p (was %d)\n", __func__, img_request,
-		atomic_read(&img_request->kref.refcount));
+		kref_read(&img_request->kref));
 	if (img_request_child_test(img_request))
 		kref_put(&img_request->kref, rbd_parent_request_destroy);
 	else

drivers/block/virtio_blk.c

@@ -770,7 +770,7 @@ static void virtblk_remove(struct virtio_device *vdev)
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
+	refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
 	put_disk(vblk->disk);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);

drivers/gpu/drm/drm_gem_cma_helper.c

@@ -376,7 +376,7 @@ void drm_gem_cma_describe(struct drm_gem_cma_object *cma_obj,
 	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%2d (%2d) %08llx %pad %p %zu",
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, &cma_obj->paddr, cma_obj->vaddr, obj->size);
 
 	seq_printf(m, "\n");

drivers/gpu/drm/drm_info.c

@@ -118,7 +118,7 @@ static int drm_gem_one_name_info(int id, void *ptr, void *data)
 	seq_printf(m, "%6d %8zd %7d %8d\n",
 		   obj->name, obj->size,
 		   obj->handle_count,
-		   atomic_read(&obj->refcount.refcount));
+		   kref_read(&obj->refcount));
 	return 0;
 }
 

drivers/gpu/drm/drm_mode_object.c

@@ -159,7 +159,7 @@ EXPORT_SYMBOL(drm_mode_object_find);
 void drm_mode_object_unreference(struct drm_mode_object *obj)
 {
 	if (obj->free_cb) {
-		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount));
+		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount));
 		kref_put(&obj->refcount, obj->free_cb);
 	}
 }
@@ -176,7 +176,7 @@ EXPORT_SYMBOL(drm_mode_object_unreference);
 void drm_mode_object_reference(struct drm_mode_object *obj)
 {
 	if (obj->free_cb) {
-		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount));
+		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount));
 		kref_get(&obj->refcount);
 	}
 }

drivers/gpu/drm/etnaviv/etnaviv_gem.c

@@ -486,7 +486,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	seq_printf(m, "%08x: %c %2d (%2d) %08lx %p %zd\n",
 			etnaviv_obj->flags, is_active(etnaviv_obj) ? 'A' : 'I',
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, etnaviv_obj->vaddr, obj->size);
 
 	rcu_read_lock();

drivers/gpu/drm/i915/i915_gem_object.h

@@ -256,7 +256,7 @@ extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
 static inline bool
 i915_gem_object_is_dead(const struct drm_i915_gem_object *obj)
 {
-	return atomic_read(&obj->base.refcount.refcount) == 0;
+	return kref_read(&obj->base.refcount) == 0;
 }
 
 static inline bool

drivers/gpu/drm/msm/msm_gem.c

@@ -642,7 +642,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p\t",
 			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, msm_obj->vaddr);
 
 	for (id = 0; id < priv->num_aspaces; id++)

drivers/gpu/drm/nouveau/nouveau_fence.c

@@ -527,7 +527,7 @@ static bool nouveau_fence_no_signaling(struct dma_fence *f)
 	 * caller should have a reference on the fence,
 	 * else fence could get freed here
 	 */
-	WARN_ON(atomic_read(&fence->base.refcount.refcount) <= 1);
+	WARN_ON(kref_read(&fence->base.refcount) <= 1);
 
 	/*
 	 * This needs uevents to work correctly, but dma_fence_add_callback relies on

drivers/gpu/drm/omapdrm/omap_gem.c

@@ -1033,7 +1033,7 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
-			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
+			omap_obj->flags, obj->name, kref_read(&obj->refcount),
 			off, &omap_obj->paddr, omap_obj->paddr_cnt,
 			omap_obj->vaddr, omap_obj->roll);