Merge tag 'drm-intel-next-2015-07-17' of git://anongit.freedesktop.org/drm-intel into drm-next

- prelim hw support dropped for skl after Damien fixed an ABI issue around
  planes
- legacy modesetting is done using atomic infrastructure now (Maarten)!
- more gen9 workarounds (Arun&Nick)
- MOCS programming (cache control for better performance) for skl/bxt
- vlv/chv dpll improvements (Ville)
- PSR fixes from Rodrigo
- fbc improvements from Paulo
- plumb requests into execlist submit functions (Mika)
- opregion code cleanup from Jani
- resource streamer support from Abdiel for mesa
- final fixes for 12bpc hdmi + enabling support from Ville
drm-intel-next-2015-07-03:
- dsi improvements (Gaurav)
- bxt ddi dpll hw state readout (Imre)
- chv dvfs support and overall wm improvements for both vlv and chv (Ville)
- ppgtt polish from Mika and Michel
- cdclk support for bxt (Bob Pauwe)
- make frontbuffer tracking more precise
- OLR removal (John Harrison)
- per-ctx WA batch buffer support (Arun Siluvery)
- remvoe KMS Kconfig option (Chris)
- more hpd handling refactoring from Jani
- use atomic states throughout modeset code and integrate with atomic plane
  update (Maarten)
drm-intel-next-2015-06-19:
- refactoring hpd irq handlers (Jani)
- polish skl dpll code a bit (Damien)
- dynamic cdclk adjustement (Ville & Mika)
- fix up 12bpc hdmi and enable it for real again (Ville)
- extend hsw cmd parser to be useful for atomic configuration (Franscico Jerez)
- even more atomic conversion and rolling state handling out across modeset code
  from Maarten & Ander
- fix DRRS idleness detection (Ramalingam)
- clean up dsp address alignment handling (Ville)
- some fbc cleanup patches from Paulo
- prevent hard-hangs when trying to reset the gpu on skl (Mika)

* tag 'drm-intel-next-2015-07-17' of git://anongit.freedesktop.org/drm-intel: (386 commits)
  drm/i915: Update DRIVER_DATE to 20150717
  drm/i915/skl: Drop the preliminary_hw_support flag
  drm/i915/skl: Don't expose the top most plane on gen9 display
  drm/i915: Fix divide by zero on watermark update
  drm/i915: Invert fastboot check
  drm/i915: Clarify logic for initial modeset
  drm/i915: Unconditionally check gmch pfit state
  drm/i915: always disable irqs in intel_pipe_update_start
  drm/i915: Remove use of runtime pm in atomic commit functions
  drm/i915: Call plane update functions directly from intel_atomic_commit.
  drm/i915: Use full atomic modeset.
  drm/i915/gen9: Add WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken
  drm/i915/gen9: Add WaFlushCoherentL3CacheLinesAtContextSwitch workaround
  drm/i915/gen9: Add WaDisableCtxRestoreArbitration workaround
  drm/i915: Enable WA batch buffers for Gen9
  drm/i915/gen9: Implement WaDisableKillLogic for gen 9
  drm/i915: Use expcitly fixed type in compat32 structs
  drm/i915: Fix noatomic crtc disabling, v2.
  drm/i915: fill in more mode members
  drm/i915: Added BXT check in HAS_CORE_RING_FREQ macro
  ...

1 files changed, 108 insertions, 52 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a7fa14516cda..923a3c4bf0b7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -677,6 +677,7 @@ eb_vma_misplaced(struct i915_vma *vma)
 static int
 i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 			    struct list_head *vmas,
+			    struct intel_context *ctx,
 			    bool *need_relocs)
 {
 	struct drm_i915_gem_object *obj;
@@ -699,6 +700,9 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 		obj = vma->obj;
 		entry = vma->exec_entry;
 
+		if (ctx->flags & CONTEXT_NO_ZEROMAP)
+			entry->flags |= __EXEC_OBJECT_NEEDS_BIAS;
+
 		if (!has_fenced_gpu_access)
 			entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
 		need_fence =
@@ -776,7 +780,8 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 				  struct drm_file *file,
 				  struct intel_engine_cs *ring,
 				  struct eb_vmas *eb,
-				  struct drm_i915_gem_exec_object2 *exec)
+				  struct drm_i915_gem_exec_object2 *exec,
+				  struct intel_context *ctx)
 {
 	struct drm_i915_gem_relocation_entry *reloc;
 	struct i915_address_space *vm;
@@ -862,7 +867,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		goto err;
 
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
 	if (ret)
 		goto err;
 
@@ -887,10 +892,10 @@ err:
 }
 
 static int
-i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
+i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 				struct list_head *vmas)
 {
-	const unsigned other_rings = ~intel_ring_flag(ring);
+	const unsigned other_rings = ~intel_ring_flag(req->ring);
 	struct i915_vma *vma;
 	uint32_t flush_domains = 0;
 	bool flush_chipset = false;
@@ -900,7 +905,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 		struct drm_i915_gem_object *obj = vma->obj;
 
 		if (obj->active & other_rings) {
-			ret = i915_gem_object_sync(obj, ring);
+			ret = i915_gem_object_sync(obj, req->ring, &req);
 			if (ret)
 				return ret;
 		}
@@ -912,7 +917,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 	}
 
 	if (flush_chipset)
-		i915_gem_chipset_flush(ring->dev);
+		i915_gem_chipset_flush(req->ring->dev);
 
 	if (flush_domains & I915_GEM_DOMAIN_GTT)
 		wmb();
@@ -920,7 +925,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 	/* Unconditionally invalidate gpu caches and ensure that we do flush
 	 * any residual writes from the previous batch.
 	 */
-	return intel_ring_invalidate_all_caches(ring);
+	return intel_ring_invalidate_all_caches(req);
 }
 
 static bool
@@ -953,6 +958,9 @@ validate_exec_list(struct drm_device *dev,
 		if (exec[i].flags & invalid_flags)
 			return -EINVAL;
 
+		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
+			return -EINVAL;
+
 		/* First check for malicious input causing overflow in
 		 * the worst case where we need to allocate the entire
 		 * relocation tree as a single array.
@@ -1013,9 +1021,9 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 
 void
 i915_gem_execbuffer_move_to_active(struct list_head *vmas,
-				   struct intel_engine_cs *ring)
+				   struct drm_i915_gem_request *req)
 {
-	struct drm_i915_gem_request *req = intel_ring_get_request(ring);
+	struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, vmas, exec_list) {
@@ -1029,12 +1037,12 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 			obj->base.pending_read_domains |= obj->base.read_domains;
 		obj->base.read_domains = obj->base.pending_read_domains;
 
-		i915_vma_move_to_active(vma, ring);
+		i915_vma_move_to_active(vma, req);
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
 			i915_gem_request_assign(&obj->last_write_req, req);
 
-			intel_fb_obj_invalidate(obj, ring, ORIGIN_CS);
+			intel_fb_obj_invalidate(obj, ORIGIN_CS);
 
 			/* update for the implicit flush after a batch */
 			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
@@ -1053,22 +1061,20 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 }
 
 void
-i915_gem_execbuffer_retire_commands(struct drm_device *dev,
-				    struct drm_file *file,
-				    struct intel_engine_cs *ring,
-				    struct drm_i915_gem_object *obj)
+i915_gem_execbuffer_retire_commands(struct i915_execbuffer_params *params)
 {
 	/* Unconditionally force add_request to emit a full flush. */
-	ring->gpu_caches_dirty = true;
+	params->ring->gpu_caches_dirty = true;
 
 	/* Add a breadcrumb for the completion of the batch buffer */
-	(void)__i915_add_request(ring, file, obj);
+	__i915_add_request(params->request, params->batch_obj, true);
 }
 
 static int
 i915_reset_gen7_sol_offsets(struct drm_device *dev,
-			    struct intel_engine_cs *ring)
+			    struct drm_i915_gem_request *req)
 {
+	struct intel_engine_cs *ring = req->ring;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret, i;
 
@@ -1077,7 +1083,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	ret = intel_ring_begin(ring, 4 * 3);
+	ret = intel_ring_begin(req, 4 * 3);
 	if (ret)
 		return ret;
 
@@ -1093,10 +1099,11 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 }
 
 static int
-i915_emit_box(struct intel_engine_cs *ring,
+i915_emit_box(struct drm_i915_gem_request *req,
 	      struct drm_clip_rect *box,
 	      int DR1, int DR4)
 {
+	struct intel_engine_cs *ring = req->ring;
 	int ret;
 
 	if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
@@ -1107,7 +1114,7 @@ i915_emit_box(struct intel_engine_cs *ring,
 	}
 
 	if (INTEL_INFO(ring->dev)->gen >= 4) {
-		ret = intel_ring_begin(ring, 4);
+		ret = intel_ring_begin(req, 4);
 		if (ret)
 			return ret;
 
@@ -1116,7 +1123,7 @@ i915_emit_box(struct intel_engine_cs *ring,
 		intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
 		intel_ring_emit(ring, DR4);
 	} else {
-		ret = intel_ring_begin(ring, 6);
+		ret = intel_ring_begin(req, 6);
 		if (ret)
 			return ret;
 
@@ -1186,17 +1193,15 @@ err:
 }
 
 int
-i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
-			       struct intel_engine_cs *ring,
-			       struct intel_context *ctx,
+i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 			       struct drm_i915_gem_execbuffer2 *args,
-			       struct list_head *vmas,
-			       struct drm_i915_gem_object *batch_obj,
-			       u64 exec_start, u32 dispatch_flags)
+			       struct list_head *vmas)
 {
 	struct drm_clip_rect *cliprects = NULL;
+	struct drm_device *dev = params->dev;
+	struct intel_engine_cs *ring = params->ring;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u64 exec_len;
+	u64 exec_start, exec_len;
 	int instp_mode;
 	u32 instp_mask;
 	int i, ret = 0;
@@ -1244,15 +1249,15 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 		}
 	}
 
-	ret = i915_gem_execbuffer_move_to_gpu(ring, vmas);
+	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
 	if (ret)
 		goto error;
 
-	ret = i915_switch_context(ring, ctx);
+	ret = i915_switch_context(params->request);
 	if (ret)
 		goto error;
 
-	WARN(ctx->ppgtt && ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
+	WARN(params->ctx->ppgtt && params->ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
 	     "%s didn't clear reload\n", ring->name);
 
 	instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
@@ -1294,7 +1299,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 
 	if (ring == &dev_priv->ring[RCS] &&
 			instp_mode != dev_priv->relative_constants_mode) {
-		ret = intel_ring_begin(ring, 4);
+		ret = intel_ring_begin(params->request, 4);
 		if (ret)
 			goto error;
 
@@ -1308,37 +1313,40 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 	}
 
 	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
-		ret = i915_reset_gen7_sol_offsets(dev, ring);
+		ret = i915_reset_gen7_sol_offsets(dev, params->request);
 		if (ret)
 			goto error;
 	}
 
-	exec_len = args->batch_len;
+	exec_len   = args->batch_len;
+	exec_start = params->batch_obj_vm_offset +
+		     params->args_batch_start_offset;
+
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
-			ret = i915_emit_box(ring, &cliprects[i],
+			ret = i915_emit_box(params->request, &cliprects[i],
 					    args->DR1, args->DR4);
 			if (ret)
 				goto error;
 
-			ret = ring->dispatch_execbuffer(ring,
+			ret = ring->dispatch_execbuffer(params->request,
 							exec_start, exec_len,
-							dispatch_flags);
+							params->dispatch_flags);
 			if (ret)
 				goto error;
 		}
 	} else {
-		ret = ring->dispatch_execbuffer(ring,
+		ret = ring->dispatch_execbuffer(params->request,
 						exec_start, exec_len,
-						dispatch_flags);
+						params->dispatch_flags);
 		if (ret)
 			return ret;
 	}
 
-	trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
+	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
 
-	i915_gem_execbuffer_move_to_active(vmas, ring);
-	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+	i915_gem_execbuffer_move_to_active(vmas, params->request);
+	i915_gem_execbuffer_retire_commands(params);
 
 error:
 	kfree(cliprects);
@@ -1408,8 +1416,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct intel_engine_cs *ring;
 	struct intel_context *ctx;
 	struct i915_address_space *vm;
+	struct i915_execbuffer_params params_master; /* XXX: will be removed later */
+	struct i915_execbuffer_params *params = &params_master;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
-	u64 exec_start = args->batch_start_offset;
 	u32 dispatch_flags;
 	int ret;
 	bool need_relocs;
@@ -1482,6 +1491,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	if (args->flags & I915_EXEC_RESOURCE_STREAMER) {
+		if (!HAS_RESOURCE_STREAMER(dev)) {
+			DRM_DEBUG("RS is only allowed for Haswell, Gen8 and above\n");
+			return -EINVAL;
+		}
+		if (ring->id != RCS) {
+			DRM_DEBUG("RS is not available on %s\n",
+				 ring->name);
+			return -EINVAL;
+		}
+
+		dispatch_flags |= I915_DISPATCH_RS;
+	}
+
 	intel_runtime_pm_get(dev_priv);
 
 	ret = i915_mutex_lock_interruptible(dev);
@@ -1502,6 +1525,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	else
 		vm = &dev_priv->gtt.base;
 
+	memset(&params_master, 0x00, sizeof(params_master));
+
 	eb = eb_create(args);
 	if (eb == NULL) {
 		i915_gem_context_unreference(ctx);
@@ -1520,7 +1545,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	/* Move the objects en-masse into the GTT, evicting if necessary. */
 	need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
-	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+	ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, ctx, &need_relocs);
 	if (ret)
 		goto err;
 
@@ -1530,7 +1555,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret) {
 		if (ret == -EFAULT) {
 			ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
-								eb, exec);
+								eb, exec, ctx);
 			BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 		}
 		if (ret)
@@ -1544,6 +1569,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		goto err;
 	}
 
+	params->args_batch_start_offset = args->batch_start_offset;
 	if (i915_needs_cmd_parser(ring) && args->batch_len) {
 		struct drm_i915_gem_object *parsed_batch_obj;
 
@@ -1575,7 +1601,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			 * command parser has accepted.
 			 */
 			dispatch_flags |= I915_DISPATCH_SECURE;
-			exec_start = 0;
+			params->args_batch_start_offset = 0;
 			batch_obj = parsed_batch_obj;
 		}
 	}
@@ -1600,15 +1626,36 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		if (ret)
 			goto err;
 
-		exec_start += i915_gem_obj_ggtt_offset(batch_obj);
+		params->batch_obj_vm_offset = i915_gem_obj_ggtt_offset(batch_obj);
 	} else
-		exec_start += i915_gem_obj_offset(batch_obj, vm);
+		params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
 
-	ret = dev_priv->gt.execbuf_submit(dev, file, ring, ctx, args,
-					  &eb->vmas, batch_obj, exec_start,
-					  dispatch_flags);
+	/* Allocate a request for this batch buffer nice and early. */
+	ret = i915_gem_request_alloc(ring, ctx, &params->request);
+	if (ret)
+		goto err_batch_unpin;
+
+	ret = i915_gem_request_add_to_client(params->request, file);
+	if (ret)
+		goto err_batch_unpin;
 
 	/*
+	 * Save assorted stuff away to pass through to *_submission().
+	 * NB: This data should be 'persistent' and not local as it will
+	 * kept around beyond the duration of the IOCTL once the GPU
+	 * scheduler arrives.
+	 */
+	params->dev                     = dev;
+	params->file                    = file;
+	params->ring                    = ring;
+	params->dispatch_flags          = dispatch_flags;
+	params->batch_obj               = batch_obj;
+	params->ctx                     = ctx;
+
+	ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
+
+err_batch_unpin:
+	/*
 	 * FIXME: We crucially rely upon the active tracking for the (ppgtt)
 	 * batch vma for correctness. For less ugly and less fragility this
 	 * needs to be adjusted to also track the ggtt batch vma properly as
@@ -1616,11 +1663,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	 */
 	if (dispatch_flags & I915_DISPATCH_SECURE)
 		i915_gem_object_ggtt_unpin(batch_obj);
+
 err:
 	/* the request owns the ref now */
 	i915_gem_context_unreference(ctx);
 	eb_destroy(eb);
 
+	/*
+	 * If the request was created but not successfully submitted then it
+	 * must be freed again. If it was submitted then it is being tracked
+	 * on the active request list and no clean up is required here.
+	 */
+	if (ret && params->request)
+		i915_gem_request_cancel(params->request);
+
 	mutex_unlock(&dev->struct_mutex);
 
 pre_mutex_err: