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, 20 insertions, 58 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 9870d83b68c1..0fff5b8cd318 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -38,6 +38,7 @@
 #include "dce/dce_6_0_sh_mask.h"
 #include "gca/gfx_7_2_enum.h"
 #include "si_enums.h"
+#include "si.h"
 
 static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -1808,17 +1809,6 @@ static int gfx_v6_0_ring_test_ring(struct amdgpu_ring *ring)
 	return r;
 }
 
-static void gfx_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
-{
-	/* flush hdp cache */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
-				 WRITE_DATA_DST_SEL(0)));
-	amdgpu_ring_write(ring, mmHDP_MEM_COHERENCY_FLUSH_CNTL);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 0x1);
-}
-
 static void gfx_v6_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
 {
 	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
@@ -1826,24 +1816,6 @@ static void gfx_v6_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
 		EVENT_INDEX(0));
 }
 
-/**
- * gfx_v6_0_ring_emit_hdp_invalidate - emit an hdp invalidate on the cp
- *
- * @adev: amdgpu_device pointer
- * @ridx: amdgpu ring index
- *
- * Emits an hdp invalidate on the cp.
- */
-static void gfx_v6_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
-				 WRITE_DATA_DST_SEL(0)));
-	amdgpu_ring_write(ring, mmHDP_DEBUG0);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 0x1);
-}
-
 static void gfx_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
 				     u64 seq, unsigned flags)
 {
@@ -2358,25 +2330,7 @@ static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 {
 	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
 
-	/* write new base address */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
-				 WRITE_DATA_DST_SEL(0)));
-	if (vmid < 8) {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vmid ));
-	} else {
-		amdgpu_ring_write(ring, (mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + (vmid - 8)));
-	}
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, pd_addr >> 12);
-
-	/* bits 0-15 are the VM contexts0-15 */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
-				 WRITE_DATA_DST_SEL(0)));
-	amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 1 << vmid);
+	amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
 
 	/* wait for the invalidate to complete */
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
@@ -2401,6 +2355,18 @@ static void gfx_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	}
 }
 
+static void gfx_v6_0_ring_emit_wreg(struct amdgpu_ring *ring,
+				    uint32_t reg, uint32_t val)
+{
+	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
+				 WRITE_DATA_DST_SEL(0)));
+	amdgpu_ring_write(ring, reg);
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, val);
+}
 
 static void gfx_v6_0_rlc_fini(struct amdgpu_device *adev)
 {
@@ -3511,23 +3477,21 @@ static const struct amdgpu_ring_funcs gfx_v6_0_ring_funcs_gfx = {
 	.get_wptr = gfx_v6_0_ring_get_wptr,
 	.set_wptr = gfx_v6_0_ring_set_wptr_gfx,
 	.emit_frame_size =
-		5 + /* gfx_v6_0_ring_emit_hdp_flush */
-		5 + /* gfx_v6_0_ring_emit_hdp_invalidate */
+		5 + 5 + /* hdp flush / invalidate */
 		14 + 14 + 14 + /* gfx_v6_0_ring_emit_fence x3 for user fence, vm fence */
 		7 + 4 + /* gfx_v6_0_ring_emit_pipeline_sync */
-		17 + 6 + /* gfx_v6_0_ring_emit_vm_flush */
+		SI_FLUSH_GPU_TLB_NUM_WREG * 5 + 7 + 6 + /* gfx_v6_0_ring_emit_vm_flush */
 		3 + 2, /* gfx_v6_ring_emit_cntxcntl including vgt flush */
 	.emit_ib_size = 6, /* gfx_v6_0_ring_emit_ib */
 	.emit_ib = gfx_v6_0_ring_emit_ib,
 	.emit_fence = gfx_v6_0_ring_emit_fence,
 	.emit_pipeline_sync = gfx_v6_0_ring_emit_pipeline_sync,
 	.emit_vm_flush = gfx_v6_0_ring_emit_vm_flush,
-	.emit_hdp_flush = gfx_v6_0_ring_emit_hdp_flush,
-	.emit_hdp_invalidate = gfx_v6_0_ring_emit_hdp_invalidate,
 	.test_ring = gfx_v6_0_ring_test_ring,
 	.test_ib = gfx_v6_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.emit_cntxcntl = gfx_v6_ring_emit_cntxcntl,
+	.emit_wreg = gfx_v6_0_ring_emit_wreg,
 };
 
 static const struct amdgpu_ring_funcs gfx_v6_0_ring_funcs_compute = {
@@ -3538,21 +3502,19 @@ static const struct amdgpu_ring_funcs gfx_v6_0_ring_funcs_compute = {
 	.get_wptr = gfx_v6_0_ring_get_wptr,
 	.set_wptr = gfx_v6_0_ring_set_wptr_compute,
 	.emit_frame_size =
-		5 + /* gfx_v6_0_ring_emit_hdp_flush */
-		5 + /* gfx_v6_0_ring_emit_hdp_invalidate */
+		5 + 5 + /* hdp flush / invalidate */
 		7 + /* gfx_v6_0_ring_emit_pipeline_sync */
-		17 + /* gfx_v6_0_ring_emit_vm_flush */
+		SI_FLUSH_GPU_TLB_NUM_WREG * 5 + 7 + /* gfx_v6_0_ring_emit_vm_flush */
 		14 + 14 + 14, /* gfx_v6_0_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 6, /* gfx_v6_0_ring_emit_ib */
 	.emit_ib = gfx_v6_0_ring_emit_ib,
 	.emit_fence = gfx_v6_0_ring_emit_fence,
 	.emit_pipeline_sync = gfx_v6_0_ring_emit_pipeline_sync,
 	.emit_vm_flush = gfx_v6_0_ring_emit_vm_flush,
-	.emit_hdp_flush = gfx_v6_0_ring_emit_hdp_flush,
-	.emit_hdp_invalidate = gfx_v6_0_ring_emit_hdp_invalidate,
 	.test_ring = gfx_v6_0_ring_test_ring,
 	.test_ib = gfx_v6_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
+	.emit_wreg = gfx_v6_0_ring_emit_wreg,
 };
 
 static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev)