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

Pull drm updates from Dave Airlie:
 "Here's the main drm pull request for 4.7, it's been a busy one, and
  I've been a bit more distracted in real life this merge window.  Lots
  more ARM drivers, not sure if it'll ever end.  I think I've at least
  one more coming the next merge window.

  But changes are all over the place, support for AMD Polaris GPUs is in
  here, some missing GM108 support for nouveau (found in some Lenovos),
  a bunch of MST and skylake fixes.

  I've also noticed a few fixes from Arnd in my inbox, that I'll try and
  get in asap, but I didn't think they should hold this up.

  New drivers:
   - Hisilicon kirin display driver
   - Mediatek MT8173 display driver
   - ARC PGU - bitstreamer on Synopsys ARC SDP boards
   - Allwinner A13 initial RGB output driver
   - Analogix driver for DisplayPort IP found in exynos and rockchip

  DRM Core:
   - UAPI headers fixes and C++ safety
   - DRM connector reference counting
   - DisplayID mode parsing for Dell 5K monitors
   - Removal of struct_mutex from drivers
   - Connector registration cleanups
   - MST robustness fixes
   - MAINTAINERS updates
   - Lockless GEM object freeing
   - Generic fbdev deferred IO support

  panel:
   - Support for a bunch of new panels

  i915:
   - VBT refactoring
   - PLL computation cleanups
   - DSI support for BXT
   - Color manager support
   - More atomic patches
   - GEM improvements
   - GuC fw loading fixes
   - DP detection fixes
   - SKL GPU hang fixes
   - Lots of BXT fixes

  radeon/amdgpu:
   - Initial Polaris support
   - GPUVM/Scheduler/Clock/Power improvements
   - ASYNC pageflip support
   - New mesa feature support

  nouveau:
   - GM108 support
   - Power sensor support improvements
   - GR init + ucode fixes.
   - Use GPU provided topology information

  vmwgfx:
   - Add host messaging support

  gma500:
   - Some cleanups and fixes

  atmel:
   - Bridge support
   - Async atomic commit support

  fsl-dcu:
   - Timing controller for LCD support
   - Pixel clock polarity support

  rcar-du:
   - Misc fixes

  exynos:
   - Pipeline clock support
   - Exynoss4533 SoC support
   - HW trigger mode support
   - export HDMI_PHY clock
   - DECON5433 fixes
   - Use generic prime functions
   - use DMA mapping APIs

  rockchip:
   - Lots of little fixes

  vc4:
   - Render node support
   - Gamma ramp support
   - DPI output support

  msm:
   - Mostly cleanups and fixes
   - Conversion to generic struct fence

  etnaviv:
   - Fix for prime buffer handling
   - Allow hangcheck to be coalesced with other wakeups

  tegra:
   - Gamme table size fix"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (1050 commits)
  drm/edid: add displayid detailed 1 timings to the modelist. (v1.1)
  drm/edid: move displayid validation to it's own function.
  drm/displayid: Iterate over all DisplayID blocks
  drm/edid: move displayid tiled block parsing into separate function.
  drm: Nuke ->vblank_disable_allowed
  drm/vmwgfx: Report vmwgfx version to vmware.log
  drm/vmwgfx: Add VMWare host messaging capability
  drm/vmwgfx: Kill some lockdep warnings
  drm/nouveau/gr/gf100-: fix race condition in fecs/gpccs ucode
  drm/nouveau/core: recognise GM108 chipsets
  drm/nouveau/gr/gm107-: fix touching non-existent ppcs in attrib cb setup
  drm/nouveau/gr/gk104-: share implementation of ppc exception init
  drm/nouveau/gr/gk104-: move rop_active_fbps init to nonctx
  drm/nouveau/bios/pll: check BIT table version before trying to parse it
  drm/nouveau/bios/pll: prevent oops when limits table can't be parsed
  drm/nouveau/volt/gk104: round up in gk104_volt_set
  drm/nouveau/fb/gm200: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gk20a,gm20b: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gf100-: allocate mmu debug buffers
  drm/nouveau/fb: allow chipset-specific actions for oneinit()
  ...

1 files changed, 51 insertions, 35 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index e3daafa1be13..39386f50af87 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -164,7 +164,6 @@ static void ttm_bo_release_list(struct kref *list_kref)
 void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
@@ -172,12 +171,11 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 
 		BUG_ON(!list_empty(&bo->lru));
 
-		man = &bdev->man[bo->mem.mem_type];
-		list_add_tail(&bo->lru, &man->lru);
+		list_add(&bo->lru, bdev->driver->lru_tail(bo));
 		kref_get(&bo->list_kref);
 
 		if (bo->ttm && !(bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) {
-			list_add_tail(&bo->swap, &bo->glob->swap_lru);
+			list_add(&bo->swap, bdev->driver->swap_lru_tail(bo));
 			kref_get(&bo->list_kref);
 		}
 	}
@@ -186,8 +184,12 @@ EXPORT_SYMBOL(ttm_bo_add_to_lru);
 
 int 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;
@@ -197,11 +199,6 @@ int ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 		++put_count;
 	}
 
-	/*
-	 * TODO: Add a driver hook to delete from
-	 * driver-specific LRU's here.
-	 */
-
 	return put_count;
 }
 
@@ -230,16 +227,32 @@ 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_add_to_lru(bo);
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
 
+struct list_head *ttm_bo_default_lru_tail(struct ttm_buffer_object *bo)
+{
+	return bo->bdev->man[bo->mem.mem_type].lru.prev;
+}
+EXPORT_SYMBOL(ttm_bo_default_lru_tail);
+
+struct list_head *ttm_bo_default_swap_lru_tail(struct ttm_buffer_object *bo)
+{
+	return bo->glob->swap_lru.prev;
+}
+EXPORT_SYMBOL(ttm_bo_default_swap_lru_tail);
+
 /*
  * Call bo->mutex locked.
  */
@@ -443,10 +456,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	int ret;
 
 	spin_lock(&glob->lru_lock);
-	ret = __ttm_bo_reserve(bo, false, true, false, NULL);
+	ret = __ttm_bo_reserve(bo, false, true, NULL);
 
 	if (!ret) {
-		if (!ttm_bo_wait(bo, false, false, true)) {
+		if (!ttm_bo_wait(bo, false, true)) {
 			put_count = ttm_bo_del_from_lru(bo);
 
 			spin_unlock(&glob->lru_lock);
@@ -499,7 +512,7 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 	int put_count;
 	int ret;
 
-	ret = ttm_bo_wait(bo, false, false, true);
+	ret = ttm_bo_wait(bo, false, true);
 
 	if (ret && !no_wait_gpu) {
 		long lret;
@@ -517,7 +530,7 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 			return -EBUSY;
 
 		spin_lock(&glob->lru_lock);
-		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
+		ret = __ttm_bo_reserve(bo, false, true, NULL);
 
 		/*
 		 * We raced, and lost, someone else holds the reservation now,
@@ -536,7 +549,7 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 		 * remove sync_obj with ttm_bo_wait, the wait should be
 		 * finished, and no new wait object should have been added.
 		 */
-		ret = ttm_bo_wait(bo, false, false, true);
+		ret = ttm_bo_wait(bo, false, true);
 		WARN_ON(ret);
 	}
 
@@ -586,11 +599,10 @@ static int ttm_bo_delayed_delete(struct ttm_bo_device *bdev, bool remove_all)
 			kref_get(&nentry->list_kref);
 		}
 
-		ret = __ttm_bo_reserve(entry, false, true, false, NULL);
+		ret = __ttm_bo_reserve(entry, false, true, NULL);
 		if (remove_all && ret) {
 			spin_unlock(&glob->lru_lock);
-			ret = __ttm_bo_reserve(entry, false, false,
-					       false, NULL);
+			ret = __ttm_bo_reserve(entry, false, false, NULL);
 			spin_lock(&glob->lru_lock);
 		}
 
@@ -676,7 +688,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	struct ttm_placement placement;
 	int ret = 0;
 
-	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
+	ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
 
 	if (unlikely(ret != 0)) {
 		if (ret != -ERESTARTSYS) {
@@ -732,7 +744,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
-		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
+		ret = __ttm_bo_reserve(bo, false, true, NULL);
 		if (!ret) {
 			if (place && (place->fpfn || place->lpfn)) {
 				/* Don't evict this BO if it's outside of the
@@ -989,13 +1001,19 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	lockdep_assert_held(&bo->resv->lock.base);
 
 	/*
-	 * FIXME: It's possible to pipeline buffer moves.
-	 * Have the driver move function wait for idle when necessary,
-	 * instead of doing it here.
+	 * Don't wait for the BO on initial allocation. This is important when
+	 * the BO has an imported reservation object.
 	 */
-	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
-	if (ret)
-		return ret;
+	if (bo->mem.mem_type != TTM_PL_SYSTEM || bo->ttm != NULL) {
+		/*
+		 * FIXME: It's possible to pipeline buffer moves.
+		 * Have the driver move function wait for idle when necessary,
+		 * instead of doing it here.
+		 */
+		ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+		if (ret)
+			return ret;
+	}
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
@@ -1206,7 +1224,7 @@ size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
 	size_t size = 0;
 
 	size += ttm_round_pot(struct_size);
-	size += PAGE_ALIGN(npages * sizeof(void *));
+	size += ttm_round_pot(npages * sizeof(void *));
 	size += ttm_round_pot(sizeof(struct ttm_tt));
 	return size;
 }
@@ -1220,8 +1238,7 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
 	size_t size = 0;
 
 	size += ttm_round_pot(struct_size);
-	size += PAGE_ALIGN(npages * sizeof(void *));
-	size += PAGE_ALIGN(npages * sizeof(dma_addr_t));
+	size += ttm_round_pot(npages * (2*sizeof(void *) + sizeof(dma_addr_t)));
 	size += ttm_round_pot(sizeof(struct ttm_dma_tt));
 	return size;
 }
@@ -1500,7 +1517,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	bdev->dev_mapping = mapping;
 	bdev->glob = glob;
 	bdev->need_dma32 = need_dma32;
-	bdev->val_seq = 0;
 	mutex_lock(&glob->device_list_mutex);
 	list_add_tail(&bdev->device_list, &glob->device_list);
 	mutex_unlock(&glob->device_list_mutex);
@@ -1554,7 +1570,7 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
 int ttm_bo_wait(struct ttm_buffer_object *bo,
-		bool lazy, bool interruptible, bool no_wait)
+		bool interruptible, bool no_wait)
 {
 	struct reservation_object_list *fobj;
 	struct reservation_object *resv;
@@ -1609,10 +1625,10 @@ int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 	 * Using ttm_bo_reserve makes sure the lru lists are updated.
 	 */
 
-	ret = ttm_bo_reserve(bo, true, no_wait, false, NULL);
+	ret = ttm_bo_reserve(bo, true, no_wait, NULL);
 	if (unlikely(ret != 0))
 		return ret;
-	ret = ttm_bo_wait(bo, false, true, no_wait);
+	ret = ttm_bo_wait(bo, true, no_wait);
 	if (likely(ret == 0))
 		atomic_inc(&bo->cpu_writers);
 	ttm_bo_unreserve(bo);
@@ -1642,7 +1658,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &glob->swap_lru, swap) {
-		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
+		ret = __ttm_bo_reserve(bo, false, true, NULL);
 		if (!ret)
 			break;
 	}
@@ -1669,7 +1685,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	 * Wait for GPU, then move to system cached.
 	 */
 
-	ret = ttm_bo_wait(bo, false, false, false);
+	ret = ttm_bo_wait(bo, false, false);
 
 	if (unlikely(ret != 0))
 		goto out;
@@ -1741,7 +1757,7 @@ int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
 		return -ERESTARTSYS;
 	if (!ww_mutex_is_locked(&bo->resv->lock))
 		goto out_unlock;
-	ret = __ttm_bo_reserve(bo, true, false, false, NULL);
+	ret = __ttm_bo_reserve(bo, true, false, NULL);
 	if (unlikely(ret != 0))
 		goto out_unlock;
 	__ttm_bo_unreserve(bo);