Merge tag 'drm-intel-next-2017-11-17-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

More change sets for 4.16:

- Many improvements for selftests and other igt tests (Chris)
- Forcewake with PUNIT->PMIC bus fixes and robustness (Hans)
- Define an engine class for uABI (Tvrtko)
- Context switch fixes and improvements (Chris)
- GT powersavings and power gating simplification and fixes (Chris)
- Other general driver clean-ups (Chris, Lucas, Ville)
- Removing old, useless and/or bad workarounds (Chris, Oscar, Radhakrishna)
- IPS, pipe config, etc in preparation for another Fast Boot attempt (Maarten)
- OA perf fixes and support to Coffee Lake and Cannonlake (Lionel)
- Fixes around GPU fault registers (Michel)
- GEM Proxy (Tina)
- Refactor of Geminilake and Cannonlake plane color handling (James)
- Generalize transcoder loop (Mika Kahola)
- New HW Workaround for Cannonlake and Geminilake (Rodrigo)
- Resume GuC before using GEM (Chris)
- Stolen Memory handling improvements (Ville)
- Initialize entry in PPAT for older compilers (Chris)
- Other fixes and robustness improvements on execbuf (Chris)
- Improve logs of GEM_BUG_ON (Mika Kuoppala)
- Rework with massive rename of GuC functions and files (Sagar)
- Don't sanitize frame start delay if pipe is off (Ville)
- Cannonlake clock fixes (Rodrigo)
- Cannonlake HDMI 2.0 support (Rodrigo)
- Add a GuC doorbells selftest (Michel)
- Add might_sleep() check to our wait_for() (Chris)

Many GVT changes for 4.16:

- CSB HWSP update support (Weinan)
- GVT debug helpers, dyndbg and debugfs (Chuanxiao, Shuo)
- full virtualized opregion (Xiaolin)
- VM health check for sane fallback (Fred)
- workload submission code refactor for future enabling (Zhi)
- Updated repo URL in MAINTAINERS (Zhenyu)
- other many misc fixes

* tag 'drm-intel-next-2017-11-17-1' of git://anongit.freedesktop.org/drm/drm-intel: (260 commits)
  drm/i915: Update DRIVER_DATE to 20171117
  drm/i915: Add a policy note for removing workarounds
  drm/i915/selftests: Report ENOMEM clearly for an allocation failure
  Revert "drm/i915: Display WA #1133 WaFbcSkipSegments:cnl, glk"
  drm/i915: Calculate g4x intermediate watermarks correctly
  drm/i915: Calculate vlv/chv intermediate watermarks correctly, v3.
  drm/i915: Pass crtc_state to ips toggle functions, v2
  drm/i915: Pass idle crtc_state to intel_dp_sink_crc
  drm/i915: Enable FIFO underrun reporting after initial fastset, v4.
  drm/i915: Mark the userptr invalidate workqueue as WQ_MEM_RECLAIM
  drm/i915: Add might_sleep() check to wait_for()
  drm/i915/selftests: Add a GuC doorbells selftest
  drm/i915/cnl: Extend HDMI 2.0 support to CNL.
  drm/i915/cnl: Simplify dco_fraction calculation.
  drm/i915/cnl: Don't blindly replace qdiv.
  drm/i915/cnl: Fix wrpll math for higher freqs.
  drm/i915/cnl: Fix, simplify and unify wrpll variable sizes.
  drm/i915/cnl: Remove useless conversion.
  drm/i915/cnl: Remove spurious central_freq.
  drm/i915/selftests: exercise_ggtt may have nothing to do
  ...

1 files changed, 85 insertions, 38 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8da1bde442dd..12e734b29463 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -28,9 +28,12 @@
  */
 
 #include <linux/log2.h>
+
 #include <drm/drmP.h>
-#include "i915_drv.h"
 #include <drm/i915_drm.h>
+
+#include "i915_drv.h"
+#include "i915_gem_render_state.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
 
@@ -480,10 +483,14 @@ static bool stop_ring(struct intel_engine_cs *engine)
 		}
 	}
 
-	I915_WRITE_CTL(engine, 0);
+	I915_WRITE_HEAD(engine, I915_READ_TAIL(engine));
+
 	I915_WRITE_HEAD(engine, 0);
 	I915_WRITE_TAIL(engine, 0);
 
+	/* The ring must be empty before it is disabled */
+	I915_WRITE_CTL(engine, 0);
+
 	return (I915_READ_HEAD(engine) & HEAD_ADDR) == 0;
 }
 
@@ -1359,12 +1366,13 @@ static int context_pin(struct i915_gem_context *ctx)
 	struct i915_vma *vma = ctx->engine[RCS].state;
 	int ret;
 
-	/* Clear this page out of any CPU caches for coherent swap-in/out.
+	/*
+	 * Clear this page out of any CPU caches for coherent swap-in/out.
 	 * We only want to do this on the first bind so that we do not stall
 	 * on an active context (which by nature is already on the GPU).
 	 */
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
-		ret = i915_gem_object_set_to_gtt_domain(vma->obj, false);
+		ret = i915_gem_object_set_to_gtt_domain(vma->obj, true);
 		if (ret)
 			return ret;
 	}
@@ -1379,11 +1387,34 @@ alloc_context_vma(struct intel_engine_cs *engine)
 	struct drm_i915_private *i915 = engine->i915;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
+	int err;
 
 	obj = i915_gem_object_create(i915, engine->context_size);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
+	if (engine->default_state) {
+		void *defaults, *vaddr;
+
+		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto err_obj;
+		}
+
+		defaults = i915_gem_object_pin_map(engine->default_state,
+						   I915_MAP_WB);
+		if (IS_ERR(defaults)) {
+			err = PTR_ERR(defaults);
+			goto err_map;
+		}
+
+		memcpy(vaddr, defaults, engine->context_size);
+
+		i915_gem_object_unpin_map(engine->default_state);
+		i915_gem_object_unpin_map(obj);
+	}
+
 	/*
 	 * Try to make the context utilize L3 as well as LLC.
 	 *
@@ -1405,10 +1436,18 @@ alloc_context_vma(struct intel_engine_cs *engine)
 	}
 
 	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
-	if (IS_ERR(vma))
-		i915_gem_object_put(obj);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
 
 	return vma;
+
+err_map:
+	i915_gem_object_unpin_map(obj);
+err_obj:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
 }
 
 static struct intel_ring *
@@ -1441,20 +1480,9 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 		if (ret)
 			goto err;
 
-		ce->state->obj->mm.dirty = true;
 		ce->state->obj->pin_global++;
 	}
 
-	/* The kernel context is only used as a placeholder for flushing the
-	 * active context. It is never used for submitting user rendering and
-	 * as such never requires the golden render context, and so we can skip
-	 * emitting it when we switch to the kernel context. This is required
-	 * as during eviction we cannot allocate and pin the renderstate in
-	 * order to initialise the context.
-	 */
-	if (i915_gem_context_is_kernel(ctx))
-		ce->initialised = true;
-
 	i915_gem_context_get(ctx);
 
 out:
@@ -1550,7 +1578,7 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv)
 
 static int ring_request_alloc(struct drm_i915_gem_request *request)
 {
-	u32 *cs;
+	int ret;
 
 	GEM_BUG_ON(!request->ctx->engine[request->engine->id].pin_count);
 
@@ -1560,37 +1588,24 @@ static int ring_request_alloc(struct drm_i915_gem_request *request)
 	 */
 	request->reserved_space += LEGACY_REQUEST_SIZE;
 
-	cs = intel_ring_begin(request, 0);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
+	ret = intel_ring_wait_for_space(request->ring, request->reserved_space);
+	if (ret)
+		return ret;
 
 	request->reserved_space -= LEGACY_REQUEST_SIZE;
 	return 0;
 }
 
-static noinline int wait_for_space(struct drm_i915_gem_request *req,
-				   unsigned int bytes)
+static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes)
 {
-	struct intel_ring *ring = req->ring;
 	struct drm_i915_gem_request *target;
 	long timeout;
 
-	lockdep_assert_held(&req->i915->drm.struct_mutex);
+	lockdep_assert_held(&ring->vma->vm->i915->drm.struct_mutex);
 
 	if (intel_ring_update_space(ring) >= bytes)
 		return 0;
 
-	/*
-	 * Space is reserved in the ringbuffer for finalising the request,
-	 * as that cannot be allowed to fail. During request finalisation,
-	 * reserved_space is set to 0 to stop the overallocation and the
-	 * assumption is that then we never need to wait (which has the
-	 * risk of failing with EINTR).
-	 *
-	 * See also i915_gem_request_alloc() and i915_add_request().
-	 */
-	GEM_BUG_ON(!req->reserved_space);
-
 	list_for_each_entry(target, &ring->request_list, ring_link) {
 		/* Would completion of this request free enough space? */
 		if (bytes <= __intel_ring_space(target->postfix,
@@ -1614,6 +1629,22 @@ static noinline int wait_for_space(struct drm_i915_gem_request *req,
 	return 0;
 }
 
+int intel_ring_wait_for_space(struct intel_ring *ring, unsigned int bytes)
+{
+	GEM_BUG_ON(bytes > ring->effective_size);
+	if (unlikely(bytes > ring->effective_size - ring->emit))
+		bytes += ring->size - ring->emit;
+
+	if (unlikely(bytes > ring->space)) {
+		int ret = wait_for_space(ring, bytes);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	GEM_BUG_ON(ring->space < bytes);
+	return 0;
+}
+
 u32 *intel_ring_begin(struct drm_i915_gem_request *req,
 		      unsigned int num_dwords)
 {
@@ -1653,7 +1684,20 @@ u32 *intel_ring_begin(struct drm_i915_gem_request *req,
 	}
 
 	if (unlikely(total_bytes > ring->space)) {
-		int ret = wait_for_space(req, total_bytes);
+		int ret;
+
+		/*
+		 * Space is reserved in the ringbuffer for finalising the
+		 * request, as that cannot be allowed to fail. During request
+		 * finalisation, reserved_space is set to 0 to stop the
+		 * overallocation and the assumption is that then we never need
+		 * to wait (which has the risk of failing with EINTR).
+		 *
+		 * See also i915_gem_request_alloc() and i915_add_request().
+		 */
+		GEM_BUG_ON(!req->reserved_space);
+
+		ret = wait_for_space(ring, total_bytes);
 		if (unlikely(ret))
 			return ERR_PTR(ret);
 	}
@@ -2028,12 +2072,15 @@ static void i9xx_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = i9xx_submit_request;
 	engine->cancel_requests = cancel_requests;
+
+	engine->park = NULL;
+	engine->unpark = NULL;
 }
 
 static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine)
 {
+	i9xx_set_default_submission(engine);
 	engine->submit_request = gen6_bsd_submit_request;
-	engine->cancel_requests = cancel_requests;
 }
 
 static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,