Merge tag 'drm-for-v4.13' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm, I think I've got one later
  driver pull for mediatek SoC driver, I'm undecided on if it needs to
  go to you yet.

  Otherwise summary below:

  Core drm:
   - Atomic add driver private objects
   - Deprecate preclose hook in modern drivers
   - MST bandwidth tracking
   - Use kvmalloc in more places
   - Add mode_valid hook for crtc/encoder/bridge
   - Reduce sync_file construction time
   - Documentation updates
   - New DRM synchronisation object support

  New drivers:
   - pl111 - pl111 CLCD display controller

  Panel:
   - Innolux P079ZCA panel driver
   - Add NL12880B20-05, NL192108AC18-02D, P320HVN03 panels
   - panel-samsung-s6e3ha2: Add s6e3hf2 panel support

  i915:
   - SKL+ watermark fixes
   - G4x/G33 reset improvements
   - DP AUX backlight improvements
   - Buffer based GuC/host communication
   - New getparam for (sub)slice infomation
   - Cannonlake and Coffeelake initial patches
   - Execbuf optimisations

  radeon/amdgpu:
   - Lots of Vega10 bug fixes
   - Preliminary raven support
   - KIQ support for compute rings
   - MEC queue management rework
   - DCE6 Audio support
   - SR-IOV improvements
   - Better radeon/amdgpu selection support

  nouveau:
   - HDMI stereoscopic support
   - Display code rework for >= GM20x GPUs

  msm:
   - GEM rework for fine-grained locking
   - Per-process pagetable work
   - HDMI fixes for Snapdragon 820.

  vc4:
   - Remove 256MB CMA limit from vc4
   - Add out-fence support
   - Add support for cygnus
   - Get/set tiling ioctls support
   - Add T-format tiling support for scanout

  zte:
   - add VGA support.

  etnaviv:
   - Thermal throttle support for newer GPUs
   - Restore userspace buffer cache performance
   - dma-buf sync fix

  stm:
   - add stm32f429 display support

  exynos:
   - Rework vblank handling
   - Fixup sw-trigger code

  sun4i:
   - V3s display engine support
   - HDMI support for older SoCs
   - Preliminary work on dual-pipeline SoCs.

  rcar-du:
   - VSP work

  imx-drm:
   - Remove counter load enable from PRE
   - Double read/write reduction flag support

  tegra:
   - Documentation for the host1x and drm driver.
   - Lots of staging ioctl fixes due to grate project work.

  omapdrm:
   - dma-buf fence support
   - TILER rotation fixes"

* tag 'drm-for-v4.13' of git://people.freedesktop.org/~airlied/linux: (1270 commits)
  drm: Remove unused drm_file parameter to drm_syncobj_replace_fence()
  drm/amd/powerplay: fix bug fail to remove sysfs when rmmod amdgpu.
  amdgpu: Set cik/si_support to 1 by default if radeon isn't built
  drm/amdgpu/gfx9: fix driver reload with KIQ
  drm/amdgpu/gfx8: fix driver reload with KIQ
  drm/amdgpu: Don't call amd_powerplay_destroy() if we don't have powerplay
  drm/ttm: Fix use-after-free in ttm_bo_clean_mm
  drm/amd/amdgpu: move get memory type function from early init to sw init
  drm/amdgpu/cgs: always set reference clock in mode_info
  drm/amdgpu: fix vblank_time when displays are off
  drm/amd/powerplay: power value format change for Vega10
  drm/amdgpu/gfx9: support the amdgpu.disable_cu option
  drm/amd/powerplay: change PPSMC_MSG_GetCurrPkgPwr for Vega10
  drm/amdgpu: Make amdgpu_cs_parser_init static (v2)
  drm/amdgpu/cs: fix a typo in a comment
  drm/amdgpu: Fix the exported always on CU bitmap
  drm/amdgpu/gfx9: gfx_v9_0_enable_gfx_static_mg_power_gating() can be static
  drm/amdgpu/psp: upper_32_bits/lower_32_bits for address setup
  drm/amd/powerplay/cz: print message if smc message fails
  drm/amdgpu: fix typo in amdgpu_debugfs_test_ib_init
  ...

1 files changed, 26 insertions, 31 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index da6f1e138e8d..814b512c6b9a 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -172,7 +172,8 @@ vc4_check_tex_size(struct vc4_exec_info *exec, struct drm_gem_cma_object *fbo,
 	 * our math.
 	 */
 	if (width > 4096 || height > 4096) {
-		DRM_ERROR("Surface dimesions (%d,%d) too large", width, height);
+		DRM_ERROR("Surface dimensions (%d,%d) too large",
+			  width, height);
 		return false;
 	}
 
@@ -348,10 +349,11 @@ static int
 validate_tile_binning_config(VALIDATE_ARGS)
 {
 	struct drm_device *dev = exec->exec_bo->base.dev;
-	struct vc4_bo *tile_bo;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint8_t flags;
-	uint32_t tile_state_size, tile_alloc_size;
-	uint32_t tile_count;
+	uint32_t tile_state_size;
+	uint32_t tile_count, bin_addr;
+	int bin_slot;
 
 	if (exec->found_tile_binning_mode_config_packet) {
 		DRM_ERROR("Duplicate VC4_PACKET_TILE_BINNING_MODE_CONFIG\n");
@@ -377,13 +379,28 @@ validate_tile_binning_config(VALIDATE_ARGS)
 		return -EINVAL;
 	}
 
+	bin_slot = vc4_v3d_get_bin_slot(vc4);
+	if (bin_slot < 0) {
+		if (bin_slot != -EINTR && bin_slot != -ERESTARTSYS) {
+			DRM_ERROR("Failed to allocate binner memory: %d\n",
+				  bin_slot);
+		}
+		return bin_slot;
+	}
+
+	/* The slot we allocated will only be used by this job, and is
+	 * free when the job completes rendering.
+	 */
+	exec->bin_slots |= BIT(bin_slot);
+	bin_addr = vc4->bin_bo->base.paddr + bin_slot * vc4->bin_alloc_size;
+
 	/* The tile state data array is 48 bytes per tile, and we put it at
 	 * the start of a BO containing both it and the tile alloc.
 	 */
 	tile_state_size = 48 * tile_count;
 
 	/* Since the tile alloc array will follow us, align. */
-	exec->tile_alloc_offset = roundup(tile_state_size, 4096);
+	exec->tile_alloc_offset = bin_addr + roundup(tile_state_size, 4096);
 
 	*(uint8_t *)(validated + 14) =
 		((flags & ~(VC4_BIN_CONFIG_ALLOC_INIT_BLOCK_SIZE_MASK |
@@ -394,35 +411,13 @@ validate_tile_binning_config(VALIDATE_ARGS)
 		 VC4_SET_FIELD(VC4_BIN_CONFIG_ALLOC_BLOCK_SIZE_128,
 			       VC4_BIN_CONFIG_ALLOC_BLOCK_SIZE));
 
-	/* Initial block size. */
-	tile_alloc_size = 32 * tile_count;
-
-	/*
-	 * The initial allocation gets rounded to the next 256 bytes before
-	 * the hardware starts fulfilling further allocations.
-	 */
-	tile_alloc_size = roundup(tile_alloc_size, 256);
-
-	/* Add space for the extra allocations.  This is what gets used first,
-	 * before overflow memory.  It must have at least 4096 bytes, but we
-	 * want to avoid overflow memory usage if possible.
-	 */
-	tile_alloc_size += 1024 * 1024;
-
-	tile_bo = vc4_bo_create(dev, exec->tile_alloc_offset + tile_alloc_size,
-				true);
-	exec->tile_bo = &tile_bo->base;
-	if (IS_ERR(exec->tile_bo))
-		return PTR_ERR(exec->tile_bo);
-	list_add_tail(&tile_bo->unref_head, &exec->unref_list);
-
 	/* tile alloc address. */
-	*(uint32_t *)(validated + 0) = (exec->tile_bo->paddr +
-					exec->tile_alloc_offset);
+	*(uint32_t *)(validated + 0) = exec->tile_alloc_offset;
 	/* tile alloc size. */
-	*(uint32_t *)(validated + 4) = tile_alloc_size;
+	*(uint32_t *)(validated + 4) = (bin_addr + vc4->bin_alloc_size -
+					exec->tile_alloc_offset);
 	/* tile state address. */
-	*(uint32_t *)(validated + 8) = exec->tile_bo->paddr;
+	*(uint32_t *)(validated + 8) = bin_addr;
 
 	return 0;
 }