Merge tag 'drm-intel-next-2016-11-08' of git://anongit.freedesktop.org/git/drm-intel into drm-next

- gpu idling rework for s/r (Imre)
- vlv mappable scanout fix
- speed up probing in resume (Lyude)
- dp audio workarounds for gen9 (Dhinakaran)
- more conversion to using dev_priv internally (Ville)
- more gen9+ wm fixes and cleanups (Maarten)
- shrinker cleanup&fixes (Chris)
- reorg plane init code (Ville)
- implement support for multiple timelines (prep work for scheduler)
  from Chris and all
- untangle dev->struct_mutex locking as prep for multiple timelines
  (Chris)
- refactor bxt phy code and collect it all in intel_dpio_phy.c (Ander)
- another gvt with bugfixes all over from Zhenyu
- piles of lspcon fixes from Imre
- 90/270 rotation fixes (Ville)
- guc log buffer support (Akash+Sagar)
- fbc fixes from Paulo
- untangle rpm vs. tiling-fences/mmaps (Chris)
- fix atomic commit to wait on the right fences (Daniel Stone)

* tag 'drm-intel-next-2016-11-08' of git://anongit.freedesktop.org/git/drm-intel: (181 commits)
  drm/i915: Update DRIVER_DATE to 20161108
  drm/i915: Mark CPU cache as dirty when used for rendering
  drm/i915: Add assert for no pending GPU requests during suspend/resume in LR mode
  drm/i915: Make sure engines are idle during GPU idling in LR mode
  drm/i915: Avoid early GPU idling due to race with new request
  drm/i915: Avoid early GPU idling due to already pending idle work
  drm/i915: Limit Valleyview and earlier to only using mappable scanout
  drm/i915: Round tile chunks up for constructing partial VMAs
  drm/i915: Remove the vma from the object list upon close
  drm/i915: Reinit polling before hpd when resuming
  drm/i915: Remove redundant reprobe in i915_drm_resume
  drm/i915/dp: Extend BDW DP audio workaround to GEN9 platforms
  drm/i915/dp: BDW cdclk fix for DP audio
  drm/i915: Fix pages pin counting around swizzle quirk
  drm/i915: Fix test on inputs for vma_compare()
  drm/i915/guc: Cache the client mapping
  drm/i915: Tidy slab cache allocations
  drm/i915: Introduce HAS_64BIT_RELOC
  drm/i915: Show the execlist queue in debugfs/i915_engine_info
  drm/i915: Unify global_list into global_link
  ...

1 files changed, 19 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c
index feebb65ba641..3af894b3d257 100644
--- a/drivers/gpu/drm/i915/gvt/render.c
+++ b/drivers/gpu/drm/i915/gvt/render.c
@@ -118,6 +118,7 @@ static u32 gen9_render_mocs_L3[32];
 static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	enum forcewake_domains fw;
 	i915_reg_t reg;
 	u32 regs[] = {
 		[RCS] = 0x4260,
@@ -135,11 +136,25 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 
 	reg = _MMIO(regs[ring_id]);
 
-	I915_WRITE(reg, 0x1);
+	/* WaForceWakeRenderDuringMmioTLBInvalidate:skl
+	 * we need to put a forcewake when invalidating RCS TLB caches,
+	 * otherwise device can go to RC6 state and interrupt invalidation
+	 * process
+	 */
+	fw = intel_uncore_forcewake_for_reg(dev_priv, reg,
+					    FW_REG_READ | FW_REG_WRITE);
+	if (ring_id == RCS && IS_SKYLAKE(dev_priv))
+		fw |= FORCEWAKE_RENDER;
 
-	if (wait_for_atomic((I915_READ(reg) == 0), 50))
+	intel_uncore_forcewake_get(dev_priv, fw);
+
+	I915_WRITE_FW(reg, 0x1);
+
+	if (wait_for_atomic((I915_READ_FW(reg) == 0), 50))
 		gvt_err("timeout in invalidate ring (%d) tlb\n", ring_id);
 
+	intel_uncore_forcewake_put(dev_priv, fw);
+
 	gvt_dbg_core("invalidate TLB for ring %d\n", ring_id);
 }
 
@@ -162,6 +177,7 @@ static void load_mocs(struct intel_vgpu *vgpu, int ring_id)
 	if (!IS_SKYLAKE(dev_priv))
 		return;
 
+	offset.reg = regs[ring_id];
 	for (i = 0; i < 64; i++) {
 		gen9_render_mocs[ring_id][i] = I915_READ(offset);
 		I915_WRITE(offset, vgpu_vreg(vgpu, offset));
@@ -199,6 +215,7 @@ static void restore_mocs(struct intel_vgpu *vgpu, int ring_id)
 	if (!IS_SKYLAKE(dev_priv))
 		return;
 
+	offset.reg = regs[ring_id];
 	for (i = 0; i < 64; i++) {
 		vgpu_vreg(vgpu, offset) = I915_READ(offset);
 		I915_WRITE(offset, gen9_render_mocs[ring_id][i]);