Merge tag 'drm-intel-fixes-2017-06-08' of git://anongit.freedesktop.org/git/drm-intel into drm-fixes

drm/i915 fixes for v4.12-rc5

* tag 'drm-intel-fixes-2017-06-08' of git://anongit.freedesktop.org/git/drm-intel:
  drm/i915: fix warning for unused variable
  drm/i915: Fix 90/270 rotated coordinates for FBC
  drm/i915: Restore has_fbc=1 for ILK-M
  drm/i915: Workaround VLV/CHV DSI scanline counter hardware fail
  drm/i915: Fix logical inversion for gen4 quirking
  drm/i915: Guard against i915_ggtt_disable_guc() being invoked unconditionally
  drm/i915: Always recompute watermarks when distrust_bios_wm is set, v2.
  drm/i915: Prevent the system suspend complete optimization
  drm/i915/psr: disable psr2 for resolution greater than 32X20
  drm/i915: Hold a wakeref for probing the ring registers
  drm/i915: Short-circuit i915_gem_wait_for_idle() if already idle
  drm/i915: Disable decoupled MMIO
  drm/i915/guc: Remove stale comment for q_fail
  drm/i915: Serialize GTT/Aperture accesses on BXT

drivers/gpu/drm/i915/i915_drv.c

@@ -1235,6 +1235,15 @@ int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_fini;
 
 	pci_set_drvdata(pdev, &dev_priv->drm);
+	/*
+	 * Disable the system suspend direct complete optimization, which can
+	 * leave the device suspended skipping the driver's suspend handlers
+	 * if the device was already runtime suspended. This is needed due to
+	 * the difference in our runtime and system suspend sequence and
+	 * becaue the HDA driver may require us to enable the audio power
+	 * domain during system suspend.
+	 */
+	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	ret = i915_driver_init_early(dev_priv, ent);
 	if (ret < 0)

drivers/gpu/drm/i915/i915_drv.h

@@ -2991,6 +2991,16 @@ static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
 	return false;
 }
 
+static inline bool
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (IS_BROXTON(dev_priv) && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
+
 int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 				int enable_ppgtt);
 

drivers/gpu/drm/i915/i915_gem.c

@@ -3298,6 +3298,10 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 {
 	int ret;
 
+	/* If the device is asleep, we have no requests outstanding */
+	if (!READ_ONCE(i915->gt.awake))
+		return 0;
+
 	if (flags & I915_WAIT_LOCKED) {
 		struct i915_gem_timeline *tl;
 

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -2191,6 +2191,101 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 		gen8_set_pte(&gtt_base[i], scratch_pte);
 }
 
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = vm->i915;
+
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct sg_table *st;
+	u64 start;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct sg_table *st,
+					     u64 start,
+					     enum i915_cache_level level,
+					     u32 unused)
+{
+	struct insert_entries arg = { vm, st, start, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  u64 start, u64 length)
 {
@@ -2785,6 +2880,14 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
 
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->base.clear_range != nop_clear_range)
+			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	return ggtt_probe_common(ggtt, size);
@@ -2997,7 +3100,8 @@ void i915_ggtt_enable_guc(struct drm_i915_private *i915)
 
 void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 {
-	i915->ggtt.invalidate = gen6_ggtt_invalidate;
+	if (i915->ggtt.invalidate == guc_ggtt_invalidate)
+		i915->ggtt.invalidate = gen6_ggtt_invalidate;
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)

drivers/gpu/drm/i915/i915_gem_tiling.c

@@ -278,7 +278,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 			obj->mm.quirked = false;
 		}
 		if (!i915_gem_object_is_tiled(obj)) {
-			GEM_BUG_ON(!obj->mm.quirked);
+			GEM_BUG_ON(obj->mm.quirked);
 			__i915_gem_object_pin_pages(obj);
 			obj->mm.quirked = true;
 		}

drivers/gpu/drm/i915/i915_pci.c

@@ -208,7 +208,7 @@ static const struct intel_device_info intel_ironlake_d_info = {
 static const struct intel_device_info intel_ironlake_m_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
-	.is_mobile = 1,
+	.is_mobile = 1, .has_fbc = 1,
 };
 
 #define GEN6_FEATURES \
@@ -390,7 +390,6 @@ static const struct intel_device_info intel_skylake_gt3_info = {
 	.has_hw_contexts = 1, \
 	.has_logical_ring_contexts = 1, \
 	.has_guc = 1, \
-	.has_decoupled_mmio = 1, \
 	.has_aliasing_ppgtt = 1, \
 	.has_full_ppgtt = 1, \
 	.has_full_48bit_ppgtt = 1, \

drivers/gpu/drm/i915/intel_display.c

@@ -12203,6 +12203,15 @@ static void update_scanline_offset(struct intel_crtc *crtc)
 	 * type. For DP ports it behaves like most other platforms, but on HDMI
 	 * there's an extra 1 line difference. So we need to add two instead of
 	 * one to the value.
+	 *
+	 * On VLV/CHV DSI the scanline counter would appear to increment
+	 * approx. 1/3 of a scanline before start of vblank. Unfortunately
+	 * that means we can't tell whether we're in vblank or not while
+	 * we're on that particular line. We must still set scanline_offset
+	 * to 1 so that the vblank timestamps come out correct when we query
+	 * the scanline counter from within the vblank interrupt handler.
+	 * However if queried just before the start of vblank we'll get an
+	 * answer that's slightly in the future.
 	 */
 	if (IS_GEN2(dev_priv)) {
 		const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;

drivers/gpu/drm/i915/intel_engine_cs.c

@@ -1075,6 +1075,22 @@ int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
 	return 0;
 }
 
+static bool ring_is_idle(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	bool idle = true;
+
+	intel_runtime_pm_get(dev_priv);
+
+	/* No bit for gen2, so assume the CS parser is idle */
+	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+		idle = false;
+
+	intel_runtime_pm_put(dev_priv);
+
+	return idle;
+}
+
 /**
  * intel_engine_is_idle() - Report if the engine has finished process all work
  * @engine: the intel_engine_cs
@@ -1084,8 +1100,6 @@ int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
  */
 bool intel_engine_is_idle(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
 	/* Any inflight/incomplete requests? */
 	if (!i915_seqno_passed(intel_engine_get_seqno(engine),
 			       intel_engine_last_submit(engine)))
@@ -1100,7 +1114,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return false;
 
 	/* Ring stopped? */
-	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+	if (!ring_is_idle(engine))
 		return false;
 
 	return true;

drivers/gpu/drm/i915/intel_fbc.c

@@ -82,20 +82,10 @@ static unsigned int get_crtc_fence_y_offset(struct intel_crtc *crtc)
 static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
-	int w, h;
-
-	if (drm_rotation_90_or_270(cache->plane.rotation)) {
-		w = cache->plane.src_h;
-		h = cache->plane.src_w;
-	} else {
-		w = cache->plane.src_w;
-		h = cache->plane.src_h;
-	}
-
 	if (width)
-		*width = w;
+		*width = cache->plane.src_w;
 	if (height)
-		*height = h;
+		*height = cache->plane.src_h;
 }
 
 static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
@@ -746,6 +736,11 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 		cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
 
 	cache->plane.rotation = plane_state->base.rotation;
+	/*
+	 * Src coordinates are already rotated by 270 degrees for
+	 * the 90/270 degree plane rotation cases (to match the
+	 * GTT mapping), hence no need to account for rotation here.
+	 */
 	cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
 	cache->plane.visible = plane_state->base.visible;

drivers/gpu/drm/i915/intel_pm.c

@@ -4335,10 +4335,18 @@ skl_compute_wm(struct drm_atomic_state *state)
 	struct drm_crtc_state *cstate;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct skl_wm_values *results = &intel_state->wm_results;
+	struct drm_device *dev = state->dev;
 	struct skl_pipe_wm *pipe_wm;
 	bool changed = false;
 	int ret, i;
 
+	/*
+	 * When we distrust bios wm we always need to recompute to set the
+	 * expected DDB allocations for each CRTC.
+	 */
+	if (to_i915(dev)->wm.distrust_bios_wm)
+		changed = true;
+
 	/*
 	 * If this transaction isn't actually touching any CRTC's, don't
 	 * bother with watermark calculation.  Note that if we pass this
@@ -4349,6 +4357,7 @@ skl_compute_wm(struct drm_atomic_state *state)
 	 */
 	for_each_new_crtc_in_state(state, crtc, cstate, i)
 		changed = true;
+
 	if (!changed)
 		return 0;
 

drivers/gpu/drm/i915/intel_psr.c

@@ -435,8 +435,9 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 	}
 
 	/* PSR2 is restricted to work with panel resolutions upto 3200x2000 */
-	if (intel_crtc->config->pipe_src_w > 3200 ||
-				intel_crtc->config->pipe_src_h > 2000) {
+	if (dev_priv->psr.psr2_support &&
+	    (intel_crtc->config->pipe_src_w > 3200 ||
+	     intel_crtc->config->pipe_src_h > 2000)) {
 		dev_priv->psr.psr2_support = false;
 		return false;
 	}

drivers/gpu/drm/i915/intel_sprite.c

@@ -83,10 +83,13 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
  */
 void intel_pipe_update_start(struct intel_crtc *crtc)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
+	bool need_vlv_dsi_wa = (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+		intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI);
 	DEFINE_WAIT(wait);
 
 	vblank_start = adjusted_mode->crtc_vblank_start;
@@ -139,6 +142,24 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 
 	drm_crtc_vblank_put(&crtc->base);
 
+	/*
+	 * On VLV/CHV DSI the scanline counter would appear to
+	 * increment approx. 1/3 of a scanline before start of vblank.
+	 * The registers still get latched at start of vblank however.
+	 * This means we must not write any registers on the first
+	 * line of vblank (since not the whole line is actually in
+	 * vblank). And unfortunately we can't use the interrupt to
+	 * wait here since it will fire too soon. We could use the
+	 * frame start interrupt instead since it will fire after the
+	 * critical scanline, but that would require more changes
+	 * in the interrupt code. So for now we'll just do the nasty
+	 * thing and poll for the bad scanline to pass us by.
+	 *
+	 * FIXME figure out if BXT+ DSI suffers from this as well
+	 */
+	while (need_vlv_dsi_wa && scanline == vblank_start)
+		scanline = intel_get_crtc_scanline(crtc);
+
 	crtc->debug.scanline_start = scanline;
 	crtc->debug.start_vbl_time = ktime_get();
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);

drivers/gpu/drm/i915/intel_uc.h

@@ -59,8 +59,6 @@ struct drm_i915_gem_request;
  *                available in the work queue (note, the queue is shared,
  *                not per-engine). It is OK for this to be nonzero, but
  *                it should not be huge!
- *   q_fail: failed to enqueue a work item. This should never happen,
- *           because we check for space beforehand.
  *   b_fail: failed to ring the doorbell. This should never happen, unless
  *           somehow the hardware misbehaves, or maybe if the GuC firmware
  *           crashes? We probably need to reset the GPU to recover.