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()
  ...

11 files changed, 29 insertions, 58 deletions

diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 1d6c335..33cd516 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/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");
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index ffb2ab3..6b68e90 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/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;
 }
 
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index 9f17085..c6885a4 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/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);
 	}
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 114dddb..aa6e35d 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/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();
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 6a368de..ecfefb9 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/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
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 8098677..1974ccb 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/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++)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index a6126c9..88ee60d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/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
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 4a90c69..74a9968 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/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);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d506361..ffc6cb5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -140,8 +140,8 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	struct ttm_bo_device *bdev = bo->bdev;
 	size_t acc_size = bo->acc_size;
 
-	BUG_ON(atomic_read(&bo->list_kref.refcount));
-	BUG_ON(atomic_read(&bo->kref.refcount));
+	BUG_ON(kref_read(&bo->list_kref));
+	BUG_ON(kref_read(&bo->kref));
 	BUG_ON(atomic_read(&bo->cpu_writers));
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
@@ -181,61 +181,46 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 }
 EXPORT_SYMBOL(ttm_bo_add_to_lru);
 
-int ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
+static void ttm_bo_ref_bug(struct kref *list_kref)
+{
+	BUG();
+}
+
+void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	int put_count = 0;
 
 	if (bdev->driver->lru_removal)
 		bdev->driver->lru_removal(bo);
 
 	if (!list_empty(&bo->swap)) {
 		list_del_init(&bo->swap);
-		++put_count;
+		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 	}
 	if (!list_empty(&bo->lru)) {
 		list_del_init(&bo->lru);
-		++put_count;
+		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 	}
-
-	return put_count;
-}
-
-static void ttm_bo_ref_bug(struct kref *list_kref)
-{
-	BUG();
-}
-
-void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count,
-			 bool never_free)
-{
-	kref_sub(&bo->list_kref, count,
-		 (never_free) ? ttm_bo_ref_bug : ttm_bo_release_list);
 }
 
 void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo)
 {
-	int put_count;
-
 	spin_lock(&bo->glob->lru_lock);
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&bo->glob->lru_lock);
-	ttm_bo_list_ref_sub(bo, put_count, true);
 }
 EXPORT_SYMBOL(ttm_bo_del_sub_from_lru);
 
 void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	int put_count = 0;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
 	if (bdev->driver->lru_removal)
 		bdev->driver->lru_removal(bo);
 
-	put_count = ttm_bo_del_from_lru(bo);
-	ttm_bo_list_ref_sub(bo, put_count, true);
+	ttm_bo_del_from_lru(bo);
 	ttm_bo_add_to_lru(bo);
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
@@ -447,7 +432,6 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bo->glob;
-	int put_count;
 	int ret;
 
 	spin_lock(&glob->lru_lock);
@@ -455,13 +439,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 
 	if (!ret) {
 		if (!ttm_bo_wait(bo, false, true)) {
-			put_count = ttm_bo_del_from_lru(bo);
-
+			ttm_bo_del_from_lru(bo);
 			spin_unlock(&glob->lru_lock);
 			ttm_bo_cleanup_memtype_use(bo);
 
-			ttm_bo_list_ref_sub(bo, put_count, true);
-
 			return;
 		} else
 			ttm_bo_flush_all_fences(bo);
@@ -504,7 +485,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 					  bool no_wait_gpu)
 {
 	struct ttm_bo_global *glob = bo->glob;
-	int put_count;
 	int ret;
 
 	ret = ttm_bo_wait(bo, false, true);
@@ -554,15 +534,13 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	list_del_init(&bo->ddestroy);
-	++put_count;
+	kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
 	spin_unlock(&glob->lru_lock);
 	ttm_bo_cleanup_memtype_use(bo);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	return 0;
 }
 
@@ -740,7 +718,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	struct ttm_bo_global *glob = bdev->glob;
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
 	struct ttm_buffer_object *bo;
-	int ret = -EBUSY, put_count;
+	int ret = -EBUSY;
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
@@ -771,13 +749,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&glob->lru_lock);
 
 	BUG_ON(ret != 0);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	ret = ttm_bo_evict(bo, interruptible, no_wait_gpu);
 	ttm_bo_unreserve(bo);
 
@@ -1669,7 +1645,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	    container_of(shrink, struct ttm_bo_global, shrink);
 	struct ttm_buffer_object *bo;
 	int ret = -EBUSY;
-	int put_count;
 	uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM);
 
 	spin_lock(&glob->lru_lock);
@@ -1692,11 +1667,9 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&glob->lru_lock);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	/**
 	 * Move to system cached
 	 */
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index d35bc49..5e1bcab 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -48,9 +48,7 @@ static void ttm_eu_del_from_lru_locked(struct list_head *list)
 
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		unsigned put_count = ttm_bo_del_from_lru(bo);
-
-		ttm_bo_list_ref_sub(bo, put_count, true);
+		ttm_bo_del_from_lru(bo);
 	}
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 4f5fa8d..fdb451e 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -304,7 +304,7 @@ bool ttm_ref_object_exists(struct ttm_object_file *tfile,
 	 * Verify that the ref->obj pointer was actually valid!
 	 */
 	rmb();
-	if (unlikely(atomic_read(&ref->kref.refcount) == 0))
+	if (unlikely(kref_read(&ref->kref) == 0))
 		goto out_false;
 
 	rcu_read_unlock();