Merge branch 'next' into for-linus

Prepare input updates for 6.6 merge window.

6 files changed, 95 insertions, 84 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 326a3d13a8295..bd5dae4d16249 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -84,6 +84,7 @@ EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
  * ttm_bo_set_bulk_move - update BOs bulk move object
  *
  * @bo: The buffer object.
+ * @bulk: bulk move structure
  *
  * Update the BOs bulk move object, making sure that resources are added/removed
  * as well. A bulk move allows to move many resource on the LRU at once,
@@ -120,8 +121,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	bool old_use_tt, new_use_tt;
 	int ret;
 
-	old_use_tt = bo->resource &&
-		ttm_manager_type(bdev, bo->resource->mem_type)->use_tt;
+	old_use_tt = !bo->resource || ttm_manager_type(bdev, bo->resource->mem_type)->use_tt;
 	new_use_tt = ttm_manager_type(bdev, mem->mem_type)->use_tt;
 
 	ttm_bo_unmap_virtual(bo);
@@ -295,8 +295,6 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 	if (unlock_resv)
 		dma_resv_unlock(bo->base.resv);
 
-	ttm_bo_put(bo);
-
 	return 0;
 }
 
@@ -465,7 +463,8 @@ bounce:
 	if (ret == -EMULTIHOP) {
 		ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop);
 		if (ret) {
-			pr_err("Buffer eviction failed\n");
+			if (ret != -ERESTARTSYS && ret != -EINTR)
+				pr_err("Buffer eviction failed\n");
 			ttm_resource_free(bo, &evict_mem);
 			goto out;
 		}
@@ -748,7 +747,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
  *
  * @bo: Pointer to a struct ttm_buffer_object. the data of which
  * we want to allocate space for.
- * @proposed_placement: Proposed new placement for the buffer object.
+ * @placement: Proposed new placement for the buffer object.
  * @mem: A struct ttm_resource.
  * @ctx: if and how to sleep, lock buffers and alloc memory
  *
@@ -894,14 +893,18 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	if (!placement->num_placement && !placement->num_busy_placement)
 		return ttm_bo_pipeline_gutting(bo);
 
-	/*
-	 * Check whether we need to move buffer.
-	 */
-	if (!bo->resource || !ttm_resource_compat(bo->resource, placement)) {
-		ret = ttm_bo_move_buffer(bo, placement, ctx);
-		if (ret)
-			return ret;
-	}
+	/* Check whether we need to move buffer. */
+	if (bo->resource && ttm_resource_compat(bo->resource, placement))
+		return 0;
+
+	/* Moving of pinned BOs is forbidden */
+	if (bo->pin_count)
+		return -EINVAL;
+
+	ret = ttm_bo_move_buffer(bo, placement, ctx);
+	if (ret)
+		return ret;
+
 	/*
 	 * We might need to add a TTM.
 	 */
@@ -953,7 +956,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, struct ttm_buffer_object *bo,
 			 struct sg_table *sg, struct dma_resv *resv,
 			 void (*destroy) (struct ttm_buffer_object *))
 {
-	static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM };
 	int ret;
 
 	kref_init(&bo->kref);
@@ -970,12 +972,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, struct ttm_buffer_object *bo,
 		bo->base.resv = &bo->base._resv;
 	atomic_inc(&ttm_glob.bo_count);
 
-	ret = ttm_resource_alloc(bo, &sys_mem, &bo->resource);
-	if (unlikely(ret)) {
-		ttm_bo_put(bo);
-		return ret;
-	}
-
 	/*
 	 * For ttm_bo_type_device buffers, allocate
 	 * address space from the device.
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 7635d7d6b13b2..fd9fd3d15101c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -157,8 +157,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	bool clear;
 	int ret = 0;
 
-	if (!src_mem)
-		return 0;
+	if (WARN_ON(!src_mem))
+		return -EINVAL;
 
 	src_man = ttm_manager_type(bdev, src_mem->mem_type);
 	if (ttm && ((ttm->page_flags & TTM_TT_FLAG_SWAPPED) ||
@@ -704,30 +704,23 @@ EXPORT_SYMBOL(ttm_bo_move_sync_cleanup);
  */
 int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 {
-	static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM };
 	struct ttm_buffer_object *ghost;
-	struct ttm_resource *sys_res;
 	struct ttm_tt *ttm;
 	int ret;
 
-	ret = ttm_resource_alloc(bo, &sys_mem, &sys_res);
-	if (ret)
-		return ret;
-
 	/* If already idle, no need for ghost object dance. */
 	if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)) {
 		if (!bo->ttm) {
 			/* See comment below about clearing. */
 			ret = ttm_tt_create(bo, true);
 			if (ret)
-				goto error_free_sys_mem;
+				return ret;
 		} else {
 			ttm_tt_unpopulate(bo->bdev, bo->ttm);
 			if (bo->type == ttm_bo_type_device)
 				ttm_tt_mark_for_clear(bo->ttm);
 		}
 		ttm_resource_free(bo, &bo->resource);
-		ttm_bo_assign_mem(bo, sys_res);
 		return 0;
 	}
 
@@ -744,7 +737,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	ret = ttm_tt_create(bo, true);
 	swap(bo->ttm, ttm);
 	if (ret)
-		goto error_free_sys_mem;
+		return ret;
 
 	ret = ttm_buffer_object_transfer(bo, &ghost);
 	if (ret)
@@ -760,13 +753,9 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	dma_resv_unlock(&ghost->base._resv);
 	ttm_bo_put(ghost);
 	bo->ttm = ttm;
-	ttm_bo_assign_mem(bo, sys_res);
 	return 0;
 
 error_destroy_tt:
 	ttm_tt_destroy(bo->bdev, ttm);
-
-error_free_sys_mem:
-	ttm_resource_free(bo, &sys_res);
 	return ret;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index ca7744b852f5e..4212b8c91dd42 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -218,14 +218,21 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 	prot = ttm_io_prot(bo, bo->resource, prot);
 	if (!bo->resource->bus.is_iomem) {
 		struct ttm_operation_ctx ctx = {
-			.interruptible = false,
+			.interruptible = true,
 			.no_wait_gpu = false,
 			.force_alloc = true
 		};
 
 		ttm = bo->ttm;
-		if (ttm_tt_populate(bdev, bo->ttm, &ctx))
-			return VM_FAULT_OOM;
+		err = ttm_tt_populate(bdev, bo->ttm, &ctx);
+		if (err) {
+			if (err == -EINTR || err == -ERESTARTSYS ||
+			    err == -EAGAIN)
+				return VM_FAULT_NOPAGE;
+
+			pr_debug("TTM fault hit %pe.\n", ERR_PTR(err));
+			return VM_FAULT_SIGBUS;
+		}
 	} else {
 		/* Iomem should not be marked encrypted */
 		prot = pgprot_decrypted(prot);
@@ -254,7 +261,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		 * encryption bits. This is because the exact location of the
 		 * data may not be known at mmap() time and may also change
 		 * at arbitrary times while the data is mmap'ed.
-		 * See vmf_insert_mixed_prot() for a discussion.
+		 * See vmf_insert_pfn_prot() for a discussion.
 		 */
 		ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
 
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index c7a1862f322a1..64a59f46f6c34 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -137,7 +137,6 @@ int ttm_global_swapout(struct ttm_operation_ctx *ctx, gfp_t gfp_flags)
 	mutex_unlock(&ttm_global_mutex);
 	return ret;
 }
-EXPORT_SYMBOL(ttm_global_swapout);
 
 int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx,
 		       gfp_t gfp_flags)
@@ -158,7 +157,7 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx,
 			struct ttm_buffer_object *bo = res->bo;
 			uint32_t num_pages;
 
-			if (!bo)
+			if (!bo || bo->resource != res)
 				continue;
 
 			num_pages = PFN_UP(bo->base.size);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index aa116a7bbae3a..4db3982057be8 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_uncached[MAX_ORDER];
+static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
+static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -368,6 +368,43 @@ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order,
 }
 
 /**
+ * ttm_pool_free_range() - Free a range of TTM pages
+ * @pool: The pool used for allocating.
+ * @tt: The struct ttm_tt holding the page pointers.
+ * @caching: The page caching mode used by the range.
+ * @start_page: index for first page to free.
+ * @end_page: index for last page to free + 1.
+ *
+ * During allocation the ttm_tt page-vector may be populated with ranges of
+ * pages with different attributes if allocation hit an error without being
+ * able to completely fulfill the allocation. This function can be used
+ * to free these individual ranges.
+ */
+static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt,
+				enum ttm_caching caching,
+				pgoff_t start_page, pgoff_t end_page)
+{
+	struct page **pages = tt->pages;
+	unsigned int order;
+	pgoff_t i, nr;
+
+	for (i = start_page; i < end_page; i += nr, pages += nr) {
+		struct ttm_pool_type *pt = NULL;
+
+		order = ttm_pool_page_order(pool, *pages);
+		nr = (1UL << order);
+		if (tt->dma_address)
+			ttm_pool_unmap(pool, tt->dma_address[i], nr);
+
+		pt = ttm_pool_select_type(pool, caching, order);
+		if (pt)
+			ttm_pool_type_give(pt, *pages);
+		else
+			ttm_pool_free_page(pool, caching, order, *pages);
+	}
+}
+
+/**
  * ttm_pool_alloc - Fill a ttm_tt object
  *
  * @pool: ttm_pool to use
@@ -382,12 +419,14 @@ static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order,
 int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 		   struct ttm_operation_ctx *ctx)
 {
-	unsigned long num_pages = tt->num_pages;
+	pgoff_t num_pages = tt->num_pages;
 	dma_addr_t *dma_addr = tt->dma_address;
 	struct page **caching = tt->pages;
 	struct page **pages = tt->pages;
+	enum ttm_caching page_caching;
 	gfp_t gfp_flags = GFP_USER;
-	unsigned int i, order;
+	pgoff_t caching_divide;
+	unsigned int order;
 	struct page *p;
 	int r;
 
@@ -405,11 +444,12 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
 
+		page_caching = tt->caching;
 		pt = ttm_pool_select_type(pool, tt->caching, order);
 		p = pt ? ttm_pool_type_take(pt) : NULL;
 		if (p) {
@@ -418,6 +458,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 			if (r)
 				goto error_free_page;
 
+			caching = pages;
 			do {
 				r = ttm_pool_page_allocated(pool, order, p,
 							    &dma_addr,
@@ -426,14 +467,15 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 				if (r)
 					goto error_free_page;
 
+				caching = pages;
 				if (num_pages < (1 << order))
 					break;
 
 				p = ttm_pool_type_take(pt);
 			} while (p);
-			caching = pages;
 		}
 
+		page_caching = ttm_cached;
 		while (num_pages >= (1 << order) &&
 		       (p = ttm_pool_alloc_page(pool, gfp_flags, order))) {
 
@@ -442,6 +484,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 							   tt->caching);
 				if (r)
 					goto error_free_page;
+				caching = pages;
 			}
 			r = ttm_pool_page_allocated(pool, order, p, &dma_addr,
 						    &num_pages, &pages);
@@ -468,15 +511,13 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	return 0;
 
 error_free_page:
-	ttm_pool_free_page(pool, tt->caching, order, p);
+	ttm_pool_free_page(pool, page_caching, order, p);
 
 error_free_all:
 	num_pages = tt->num_pages - num_pages;
-	for (i = 0; i < num_pages; ) {
-		order = ttm_pool_page_order(pool, tt->pages[i]);
-		ttm_pool_free_page(pool, tt->caching, order, tt->pages[i]);
-		i += 1 << order;
-	}
+	caching_divide = caching - tt->pages;
+	ttm_pool_free_range(pool, tt, tt->caching, 0, caching_divide);
+	ttm_pool_free_range(pool, tt, ttm_cached, caching_divide, num_pages);
 
 	return r;
 }
@@ -492,27 +533,7 @@ EXPORT_SYMBOL(ttm_pool_alloc);
  */
 void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt)
 {
-	unsigned int i;
-
-	for (i = 0; i < tt->num_pages; ) {
-		struct page *p = tt->pages[i];
-		unsigned int order, num_pages;
-		struct ttm_pool_type *pt;
-
-		order = ttm_pool_page_order(pool, p);
-		num_pages = 1ULL << order;
-		if (tt->dma_address)
-			ttm_pool_unmap(pool, tt->dma_address[i], num_pages);
-
-		pt = ttm_pool_select_type(pool, tt->caching, order);
-		if (pt)
-			ttm_pool_type_give(pt, tt->pages[i]);
-		else
-			ttm_pool_free_page(pool, tt->caching, order,
-					   tt->pages[i]);
-
-		i += num_pages;
-	}
+	ttm_pool_free_range(pool, tt, tt->caching, 0, tt->num_pages);
 
 	while (atomic_long_read(&allocated_pages) > page_pool_size)
 		ttm_pool_shrink();
@@ -542,7 +563,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -562,7 +583,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -616,7 +637,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -627,7 +648,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -736,7 +757,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -769,7 +790,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index b8a826a24fb2c..7333f7a87a2fb 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -361,7 +361,6 @@ bool ttm_resource_compat(struct ttm_resource *res,
 
 	return false;
 }
-EXPORT_SYMBOL(ttm_resource_compat);
 
 void ttm_resource_set_bo(struct ttm_resource *res,
 			 struct ttm_buffer_object *bo)