Merge branch 'drm-radeon-kms' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6

* 'drm-radeon-kms' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: (35 commits)
  drm/radeon: set fb aperture sizes for framebuffer handoff.
  drm/ttm: fix highuser vs dma32 confusion.
  drm/radeon: Fix size used for benchmarking BO copies.
  drm/radeon: Add radeon.test parameter for running BO GPU copy tests.
  drm/radeon/kms: allow interruptible waits for objects.
  drm/ttm: powerpc: Fix Highmem cache flushing.
  x86: Export kmap_atomic_prot() needed for TTM.
  drm/ttm: Fix ttm in-kernel copying of pages with non-standard caching attributes.
  drm/ttm: Fix an oops and sync object leak.
  drm/radeon/kms: vram sizing on certain r100 chips needs workaround.
  drm/radeon: Pay more attention to object placement requested by userspace.
  drm/radeon: Fall back to evicting BOs with memcpy if necessary.
  drm/radeon: Don't unreserve twice on failure to validate.
  drm/radeon/kms: fix bandwidth computation on avivo hardware
  drm/radeon/kms: add initial colortiling support.
  drm/radeon/kms: fix hotspot handling on pre-avivo chips
  drm/radeon/kms: enable frac fb divs on rs600/rs690/rs740
  drm/radeon/kms: add PLL flag to prefer frequencies <= the target freq
  drm/radeon/kms: block RN50 from using 3D engine.
  drm/radeon/kms: fix VRAM sizing like DDX does it.
  ...

4 files changed, 127 insertions, 33 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c1c407f7cca3..6538d4236989 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -43,7 +43,6 @@
 #define TTM_BO_HASH_ORDER 13
 
 static int ttm_bo_setup_vm(struct ttm_buffer_object *bo);
-static void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo);
 static int ttm_bo_swapout(struct ttm_mem_shrink *shrink);
 
 static inline uint32_t ttm_bo_type_flags(unsigned type)
@@ -224,6 +223,9 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc)
 	TTM_ASSERT_LOCKED(&bo->mutex);
 	bo->ttm = NULL;
 
+	if (bdev->need_dma32)
+		page_flags |= TTM_PAGE_FLAG_DMA32;
+
 	switch (bo->type) {
 	case ttm_bo_type_device:
 		if (zero_alloc)
@@ -304,6 +306,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	}
 
+	if (bdev->driver->move_notify)
+		bdev->driver->move_notify(bo, mem);
+
 	if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
 	    !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
 		ret = ttm_bo_move_ttm(bo, evict, no_wait, mem);
@@ -655,31 +660,52 @@ retry_pre_get:
 	return 0;
 }
 
+static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
+				      uint32_t cur_placement,
+				      uint32_t proposed_placement)
+{
+	uint32_t caching = proposed_placement & TTM_PL_MASK_CACHING;
+	uint32_t result = proposed_placement & ~TTM_PL_MASK_CACHING;
+
+	/**
+	 * Keep current caching if possible.
+	 */
+
+	if ((cur_placement & caching) != 0)
+		result |= (cur_placement & caching);
+	else if ((man->default_caching & caching) != 0)
+		result |= man->default_caching;
+	else if ((TTM_PL_FLAG_CACHED & caching) != 0)
+		result |= TTM_PL_FLAG_CACHED;
+	else if ((TTM_PL_FLAG_WC & caching) != 0)
+		result |= TTM_PL_FLAG_WC;
+	else if ((TTM_PL_FLAG_UNCACHED & caching) != 0)
+		result |= TTM_PL_FLAG_UNCACHED;
+
+	return result;
+}
+
+
 static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
 				 bool disallow_fixed,
 				 uint32_t mem_type,
-				 uint32_t mask, uint32_t *res_mask)
+				 uint32_t proposed_placement,
+				 uint32_t *masked_placement)
 {
 	uint32_t cur_flags = ttm_bo_type_flags(mem_type);
 
 	if ((man->flags & TTM_MEMTYPE_FLAG_FIXED) && disallow_fixed)
 		return false;
 
-	if ((cur_flags & mask & TTM_PL_MASK_MEM) == 0)
+	if ((cur_flags & proposed_placement & TTM_PL_MASK_MEM) == 0)
 		return false;
 
-	if ((mask & man->available_caching) == 0)
+	if ((proposed_placement & man->available_caching) == 0)
 		return false;
-	if (mask & man->default_caching)
-		cur_flags |= man->default_caching;
-	else if (mask & TTM_PL_FLAG_CACHED)
-		cur_flags |= TTM_PL_FLAG_CACHED;
-	else if (mask & TTM_PL_FLAG_WC)
-		cur_flags |= TTM_PL_FLAG_WC;
-	else
-		cur_flags |= TTM_PL_FLAG_UNCACHED;
 
-	*res_mask = cur_flags;
+	cur_flags |= (proposed_placement & man->available_caching);
+
+	*masked_placement = cur_flags;
 	return true;
 }
 
@@ -723,6 +749,9 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (!type_ok)
 			continue;
 
+		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
+						  cur_flags);
+
 		if (mem_type == TTM_PL_SYSTEM)
 			break;
 
@@ -779,6 +808,9 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 					  proposed_placement, &cur_flags))
 			continue;
 
+		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
+						  cur_flags);
+
 		ret = ttm_bo_mem_force_space(bdev, mem, mem_type,
 					     interruptible, no_wait);
 
@@ -1305,7 +1337,8 @@ EXPORT_SYMBOL(ttm_bo_device_release);
 
 int ttm_bo_device_init(struct ttm_bo_device *bdev,
 		       struct ttm_mem_global *mem_glob,
-		       struct ttm_bo_driver *driver, uint64_t file_page_offset)
+		       struct ttm_bo_driver *driver, uint64_t file_page_offset,
+		       bool need_dma32)
 {
 	int ret = -EINVAL;
 
@@ -1342,6 +1375,7 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bdev->ddestroy);
 	INIT_LIST_HEAD(&bdev->swap_lru);
 	bdev->dev_mapping = NULL;
+	bdev->need_dma32 = need_dma32;
 	ttm_mem_init_shrink(&bdev->shrink, ttm_bo_swapout);
 	ret = ttm_mem_register_shrink(mem_glob, &bdev->shrink);
 	if (unlikely(ret != 0)) {
@@ -1419,6 +1453,7 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 
 	unmap_mapping_range(bdev->dev_mapping, offset, holelen, 1);
 }
+EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
 static void ttm_bo_vm_insert_rb(struct ttm_buffer_object *bo)
 {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index bdec583901eb..ce2e6f38ea01 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -136,7 +136,8 @@ static int ttm_copy_io_page(void *dst, void *src, unsigned long page)
 }
 
 static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
-				unsigned long page)
+				unsigned long page,
+				pgprot_t prot)
 {
 	struct page *d = ttm_tt_get_page(ttm, page);
 	void *dst;
@@ -145,17 +146,35 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src,
 		return -ENOMEM;
 
 	src = (void *)((unsigned long)src + (page << PAGE_SHIFT));
-	dst = kmap(d);
+
+#ifdef CONFIG_X86
+	dst = kmap_atomic_prot(d, KM_USER0, prot);
+#else
+	if (prot != PAGE_KERNEL)
+		dst = vmap(&d, 1, 0, prot);
+	else
+		dst = kmap(d);
+#endif
 	if (!dst)
 		return -ENOMEM;
 
 	memcpy_fromio(dst, src, PAGE_SIZE);
-	kunmap(d);
+
+#ifdef CONFIG_X86
+	kunmap_atomic(dst, KM_USER0);
+#else
+	if (prot != PAGE_KERNEL)
+		vunmap(dst);
+	else
+		kunmap(d);
+#endif
+
 	return 0;
 }
 
 static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
-				unsigned long page)
+				unsigned long page,
+				pgprot_t prot)
 {
 	struct page *s = ttm_tt_get_page(ttm, page);
 	void *src;
@@ -164,12 +183,28 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
 		return -ENOMEM;
 
 	dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT));
-	src = kmap(s);
+#ifdef CONFIG_X86
+	src = kmap_atomic_prot(s, KM_USER0, prot);
+#else
+	if (prot != PAGE_KERNEL)
+		src = vmap(&s, 1, 0, prot);
+	else
+		src = kmap(s);
+#endif
 	if (!src)
 		return -ENOMEM;
 
 	memcpy_toio(dst, src, PAGE_SIZE);
-	kunmap(s);
+
+#ifdef CONFIG_X86
+	kunmap_atomic(src, KM_USER0);
+#else
+	if (prot != PAGE_KERNEL)
+		vunmap(src);
+	else
+		kunmap(s);
+#endif
+
 	return 0;
 }
 
@@ -214,11 +249,17 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 
 	for (i = 0; i < new_mem->num_pages; ++i) {
 		page = i * dir + add;
-		if (old_iomap == NULL)
-			ret = ttm_copy_ttm_io_page(ttm, new_iomap, page);
-		else if (new_iomap == NULL)
-			ret = ttm_copy_io_ttm_page(ttm, old_iomap, page);
-		else
+		if (old_iomap == NULL) {
+			pgprot_t prot = ttm_io_prot(old_mem->placement,
+						    PAGE_KERNEL);
+			ret = ttm_copy_ttm_io_page(ttm, new_iomap, page,
+						   prot);
+		} else if (new_iomap == NULL) {
+			pgprot_t prot = ttm_io_prot(new_mem->placement,
+						    PAGE_KERNEL);
+			ret = ttm_copy_io_ttm_page(ttm, old_iomap, page,
+						   prot);
+		} else
 			ret = ttm_copy_io_page(new_iomap, old_iomap, page);
 		if (ret)
 			goto out1;
@@ -509,8 +550,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 	if (evict) {
 		ret = ttm_bo_wait(bo, false, false, false);
 		spin_unlock(&bo->lock);
-		driver->sync_obj_unref(&bo->sync_obj);
-
+		if (tmp_obj)
+			driver->sync_obj_unref(&tmp_obj);
 		if (ret)
 			return ret;
 
@@ -532,6 +573,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 
 		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
 		spin_unlock(&bo->lock);
+		if (tmp_obj)
+			driver->sync_obj_unref(&tmp_obj);
 
 		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		if (ret)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index fe949a12fe40..33de7637c0c6 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -101,6 +101,9 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_NOPAGE;
 	}
 
+	if (bdev->driver->fault_reserve_notify)
+		bdev->driver->fault_reserve_notify(bo);
+
 	/*
 	 * Wait for buffer data in transit, due to a pipelined
 	 * move.
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 75dc8bd24592..b8b6c4a5f983 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -86,10 +86,16 @@ void ttm_tt_cache_flush(struct page *pages[], unsigned long num_pages)
 	unsigned long i;
 
 	for (i = 0; i < num_pages; ++i) {
-		if (pages[i]) {
-			unsigned long start = (unsigned long)page_address(pages[i]);
-			flush_dcache_range(start, start + PAGE_SIZE);
-		}
+		struct page *page = pages[i];
+		void *page_virtual;
+
+		if (unlikely(page == NULL))
+			continue;
+
+		page_virtual = kmap_atomic(page, KM_USER0);
+		flush_dcache_range((unsigned long) page_virtual,
+				   (unsigned long) page_virtual + PAGE_SIZE);
+		kunmap_atomic(page_virtual, KM_USER0);
 	}
 #else
 	if (on_each_cpu(ttm_tt_ipi_handler, NULL, 1) != 0)
@@ -131,10 +137,17 @@ static void ttm_tt_free_page_directory(struct ttm_tt *ttm)
 
 static struct page *ttm_tt_alloc_page(unsigned page_flags)
 {
+	gfp_t gfp_flags = GFP_USER;
+
 	if (page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)
-		return alloc_page(GFP_HIGHUSER | __GFP_ZERO);
+		gfp_flags |= __GFP_ZERO;
+
+	if (page_flags & TTM_PAGE_FLAG_DMA32)
+		gfp_flags |= __GFP_DMA32;
+	else
+		gfp_flags |= __GFP_HIGHMEM;
 
-	return alloc_page(GFP_HIGHUSER);
+	return alloc_page(gfp_flags);
 }
 
 static void ttm_tt_free_user_pages(struct ttm_tt *ttm)