Merge branch 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux into drm-next

First feature pull for 4.15.  Highlights:
- Per VM BO support
- Lots of powerplay cleanups
- Powerplay support for CI
- pasid mgr for kfd
- interrupt infrastructure for recoverable page faults
- SR-IOV fixes
- initial GPU reset for vega10
- prime mmap support
- ttm page table debugging improvements
- lots of bug fixes

* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (232 commits)
  drm/amdgpu: clarify license in amdgpu_trace_points.c
  drm/amdgpu: Add gem_prime_mmap support
  drm/amd/powerplay: delete dead code in smumgr
  drm/amd/powerplay: delete SMUM_FIELD_MASK
  drm/amd/powerplay: delete SMUM_WAIT_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_READ_FIELD
  drm/amd/powerplay: delete SMUM_SET_FIELD
  drm/amd/powerplay: delete SMUM_READ_VFPF_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_WRITE_VFPF_INDIRECT_FIELD
  drm/amd/powerplay: delete SMUM_WRITE_FIELD
  drm/amd/powerplay: delete SMU_WRITE_INDIRECT_FIELD
  drm/amd/powerplay: move macros to hwmgr.h
  drm/amd/powerplay: move PHM_WAIT_VFPF_INDIRECT_FIELD to hwmgr.h
  drm/amd/powerplay: move SMUM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL to hwmgr.h
  drm/amd/powerplay: move SMUM_WAIT_INDIRECT_FIELD_UNEQUAL to hwmgr.h
  drm/amd/powerplay: add new helper functions in hwmgr.h
  drm/amd/powerplay: use SMU_IND_INDEX/DATA_11 pair
  drm/amd/powerplay: refine powerplay code.
  drm/amd/powerplay: delete dead code in hwmgr.h
  drm/amd/powerplay: refine interface in struct pp_smumgr_func
  ...

4 files changed, 78 insertions, 42 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 180ce6296416..d79607a1187c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -440,28 +440,29 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	struct ttm_bo_global *glob = bo->glob;
 	int ret;
 
+	ret = ttm_bo_individualize_resv(bo);
+	if (ret) {
+		/* Last resort, if we fail to allocate memory for the
+		 * fences block for the BO to become idle
+		 */
+		reservation_object_wait_timeout_rcu(bo->resv, true, false,
+						    30 * HZ);
+		spin_lock(&glob->lru_lock);
+		goto error;
+	}
+
 	spin_lock(&glob->lru_lock);
 	ret = __ttm_bo_reserve(bo, false, true, NULL);
-
 	if (!ret) {
-		if (!ttm_bo_wait(bo, false, true)) {
+		if (reservation_object_test_signaled_rcu(&bo->ttm_resv, true)) {
 			ttm_bo_del_from_lru(bo);
 			spin_unlock(&glob->lru_lock);
+			if (bo->resv != &bo->ttm_resv)
+				reservation_object_unlock(&bo->ttm_resv);
 			ttm_bo_cleanup_memtype_use(bo);
-
 			return;
 		}
 
-		ret = ttm_bo_individualize_resv(bo);
-		if (ret) {
-			/* Last resort, if we fail to allocate memory for the
-			 * fences block for the BO to become idle and free it.
-			 */
-			spin_unlock(&glob->lru_lock);
-			ttm_bo_wait(bo, true, true);
-			ttm_bo_cleanup_memtype_use(bo);
-			return;
-		}
 		ttm_bo_flush_all_fences(bo);
 
 		/*
@@ -474,11 +475,12 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 			ttm_bo_add_to_lru(bo);
 		}
 
-		if (bo->resv != &bo->ttm_resv)
-			reservation_object_unlock(&bo->ttm_resv);
 		__ttm_bo_unreserve(bo);
 	}
+	if (bo->resv != &bo->ttm_resv)
+		reservation_object_unlock(&bo->ttm_resv);
 
+error:
 	kref_get(&bo->list_kref);
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
 	spin_unlock(&glob->lru_lock);
@@ -555,6 +557,8 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 	}
 
 	ttm_bo_del_from_lru(bo);
+	if (!list_empty(&bo->ddestroy) && (bo->resv != &bo->ttm_resv))
+		reservation_object_fini(&bo->ttm_resv);
 	list_del_init(&bo->ddestroy);
 	kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index c934ad5b3903..78cb99be7146 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -587,7 +587,6 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 	unsigned long offset, size;
 	int ret;
 
-	BUG_ON(!list_empty(&bo->swap));
 	map->virtual = NULL;
 	map->bo = bo;
 	if (num_pages > bo->num_pages)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 871599826773..052e1f102113 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -920,6 +920,49 @@ void ttm_pool_unpopulate(struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_pool_unpopulate);
 
+#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
+int ttm_populate_and_map_pages(struct device *dev, struct ttm_dma_tt *tt)
+{
+	unsigned i;
+	int r;
+
+	r = ttm_pool_populate(&tt->ttm);
+	if (r)
+		return r;
+
+	for (i = 0; i < tt->ttm.num_pages; i++) {
+		tt->dma_address[i] = dma_map_page(dev, tt->ttm.pages[i],
+						  0, PAGE_SIZE,
+						  DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(dev, tt->dma_address[i])) {
+			while (i--) {
+				dma_unmap_page(dev, tt->dma_address[i],
+					       PAGE_SIZE, DMA_BIDIRECTIONAL);
+				tt->dma_address[i] = 0;
+			}
+			ttm_pool_unpopulate(&tt->ttm);
+			return -EFAULT;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(ttm_populate_and_map_pages);
+
+void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt)
+{
+	unsigned i;
+	
+	for (i = 0; i < tt->ttm.num_pages; i++) {
+		if (tt->dma_address[i]) {
+			dma_unmap_page(dev, tt->dma_address[i],
+				       PAGE_SIZE, DMA_BIDIRECTIONAL);
+		}
+	}
+	ttm_pool_unpopulate(&tt->ttm);
+}
+EXPORT_SYMBOL(ttm_unmap_and_unpopulate_pages);
+#endif
+
 int ttm_page_alloc_debugfs(struct seq_file *m, void *data)
 {
 	struct ttm_page_pool *p;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 90ddbdca93bd..06bc14b55e66 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -60,22 +60,15 @@
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		4
 #define FREE_ALL_PAGES			(~0U)
-/* times are in msecs */
-#define IS_UNDEFINED			(0)
-#define IS_WC				(1<<1)
-#define IS_UC				(1<<2)
-#define IS_CACHED			(1<<3)
-#define IS_DMA32			(1<<4)
 
 enum pool_type {
-	POOL_IS_UNDEFINED,
-	POOL_IS_WC = IS_WC,
-	POOL_IS_UC = IS_UC,
-	POOL_IS_CACHED = IS_CACHED,
-	POOL_IS_WC_DMA32 = IS_WC | IS_DMA32,
-	POOL_IS_UC_DMA32 = IS_UC | IS_DMA32,
-	POOL_IS_CACHED_DMA32 = IS_CACHED | IS_DMA32,
+	IS_UNDEFINED	= 0,
+	IS_WC		= 1 << 1,
+	IS_UC		= 1 << 2,
+	IS_CACHED	= 1 << 3,
+	IS_DMA32	= 1 << 4
 };
+
 /*
  * The pool structure. There are usually six pools:
  *  - generic (not restricted to DMA32):
@@ -86,11 +79,9 @@ enum pool_type {
  * The other ones can be shrunk by the shrinker API if neccessary.
  * @pools: The 'struct device->dma_pools' link.
  * @type: Type of the pool
- * @lock: Protects the inuse_list and free_list from concurrnet access. Must be
+ * @lock: Protects the free_list from concurrnet access. Must be
  * used with irqsave/irqrestore variants because pool allocator maybe called
  * from delayed work.
- * @inuse_list: Pool of pages that are in use. The order is very important and
- *   it is in the order that the TTM pages that are put back are in.
  * @free_list: Pool of pages that are free to be used. No order requirements.
  * @dev: The device that is associated with these pools.
  * @size: Size used during DMA allocation.
@@ -107,7 +98,6 @@ struct dma_pool {
 	struct list_head pools; /* The 'struct device->dma_pools link */
 	enum pool_type type;
 	spinlock_t lock;
-	struct list_head inuse_list;
 	struct list_head free_list;
 	struct device *dev;
 	unsigned size;
@@ -609,7 +599,6 @@ static struct dma_pool *ttm_dma_pool_init(struct device *dev, gfp_t flags,
 	sec_pool->pool =  pool;
 
 	INIT_LIST_HEAD(&pool->free_list);
-	INIT_LIST_HEAD(&pool->inuse_list);
 	INIT_LIST_HEAD(&pool->pools);
 	spin_lock_init(&pool->lock);
 	pool->dev = dev;
@@ -882,22 +871,23 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	struct dma_pool *pool;
 	enum pool_type type;
 	unsigned i;
-	gfp_t gfp_flags;
 	int ret;
 
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
 	type = ttm_to_type(ttm->page_flags, ttm->caching_state);
-	if (ttm->page_flags & TTM_PAGE_FLAG_DMA32)
-		gfp_flags = GFP_USER | GFP_DMA32;
-	else
-		gfp_flags = GFP_HIGHUSER;
-	if (ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
-		gfp_flags |= __GFP_ZERO;
-
 	pool = ttm_dma_find_pool(dev, type);
 	if (!pool) {
+		gfp_t gfp_flags;
+
+		if (ttm->page_flags & TTM_PAGE_FLAG_DMA32)
+			gfp_flags = GFP_USER | GFP_DMA32;
+		else
+			gfp_flags = GFP_HIGHUSER;
+		if (ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
+			gfp_flags |= __GFP_ZERO;
+
 		pool = ttm_dma_pool_init(dev, gfp_flags, type);
 		if (IS_ERR_OR_NULL(pool)) {
 			return -ENOMEM;