Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 15 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 9a29c1399091..b75d901ba3c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -24,6 +24,7 @@
 #include <drm/drmP.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "si.h"
 #include "sid.h"
 
 const u32 sdma_offsets[SDMA_MAX_INSTANCE] =
@@ -74,20 +75,6 @@ static void si_dma_ring_emit_ib(struct amdgpu_ring *ring,
 
 }
 
-static void si_dma_ring_emit_hdp_flush(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	amdgpu_ring_write(ring, (0xf << 16) | (HDP_MEM_COHERENCY_FLUSH_CNTL));
-	amdgpu_ring_write(ring, 1);
-}
-
-static void si_dma_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	amdgpu_ring_write(ring, (0xf << 16) | (HDP_DEBUG0));
-	amdgpu_ring_write(ring, 1);
-}
-
 /**
  * si_dma_ring_emit_fence - emit a fence on the DMA ring
  *
@@ -134,7 +121,7 @@ static void si_dma_stop(struct amdgpu_device *adev)
 		WREG32(DMA_RB_CNTL + sdma_offsets[i], rb_cntl);
 
 		if (adev->mman.buffer_funcs_ring == ring)
-			amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
+			amdgpu_ttm_set_buffer_funcs_status(adev, false);
 		ring->ready = false;
 	}
 }
@@ -197,7 +184,7 @@ static int si_dma_start(struct amdgpu_device *adev)
 		}
 
 		if (adev->mman.buffer_funcs_ring == ring)
-			amdgpu_ttm_set_active_vram_size(adev, adev->mc.real_vram_size);
+			amdgpu_ttm_set_buffer_funcs_status(adev, true);
 	}
 
 	return 0;
@@ -475,17 +462,7 @@ static void si_dma_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 static void si_dma_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				      unsigned vmid, uint64_t pd_addr)
 {
-	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	if (vmid < 8)
-		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid));
-	else
-		amdgpu_ring_write(ring, (0xf << 16) | (VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vmid - 8)));
-	amdgpu_ring_write(ring, pd_addr >> 12);
-
-	/* bits 0-7 are the VM contexts0-7 */
-	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
-	amdgpu_ring_write(ring, (0xf << 16) | (VM_INVALIDATE_REQUEST));
-	amdgpu_ring_write(ring, 1 << vmid);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for invalidate to complete */
 	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_POLL_REG_MEM, 0, 0, 0, 0));
@@ -496,6 +473,14 @@ static void si_dma_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, (0 << 28) | 0x20); /* func(always) | poll interval */
 }
 
+static void si_dma_ring_emit_wreg(struct amdgpu_ring *ring,
+				  uint32_t reg, uint32_t val)
+{
+	amdgpu_ring_write(ring, DMA_PACKET(DMA_PACKET_SRBM_WRITE, 0, 0, 0, 0));
+	amdgpu_ring_write(ring, (0xf << 16) | reg);
+	amdgpu_ring_write(ring, val);
+}
+
 static int si_dma_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -772,22 +757,20 @@ static const struct amdgpu_ring_funcs si_dma_ring_funcs = {
 	.get_wptr = si_dma_ring_get_wptr,
 	.set_wptr = si_dma_ring_set_wptr,
 	.emit_frame_size =
-		3 + /* si_dma_ring_emit_hdp_flush */
-		3 + /* si_dma_ring_emit_hdp_invalidate */
+		3 + 3 + /* hdp flush / invalidate */
 		6 + /* si_dma_ring_emit_pipeline_sync */
-		12 + /* si_dma_ring_emit_vm_flush */
+		SI_FLUSH_GPU_TLB_NUM_WREG * 3 + 6 + /* si_dma_ring_emit_vm_flush */
 		9 + 9 + 9, /* si_dma_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 7 + 3, /* si_dma_ring_emit_ib */
 	.emit_ib = si_dma_ring_emit_ib,
 	.emit_fence = si_dma_ring_emit_fence,
 	.emit_pipeline_sync = si_dma_ring_emit_pipeline_sync,
 	.emit_vm_flush = si_dma_ring_emit_vm_flush,
-	.emit_hdp_flush = si_dma_ring_emit_hdp_flush,
-	.emit_hdp_invalidate = si_dma_ring_emit_hdp_invalidate,
 	.test_ring = si_dma_ring_test_ring,
 	.test_ib = si_dma_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = si_dma_ring_pad_ib,
+	.emit_wreg = si_dma_ring_emit_wreg,
 };
 
 static void si_dma_set_ring_funcs(struct amdgpu_device *adev)
@@ -891,9 +874,6 @@ static const struct amdgpu_vm_pte_funcs si_dma_vm_pte_funcs = {
 	.copy_pte = si_dma_vm_copy_pte,
 
 	.write_pte = si_dma_vm_write_pte,
-
-	.set_max_nums_pte_pde = 0xffff8 >> 3,
-	.set_pte_pde_num_dw = 9,
 	.set_pte_pde = si_dma_vm_set_pte_pde,
 };