Merge tag 'drm-intel-next-fixes-2016-01-14' of git://anongit.freedesktop.org/drm-intel into drm-next

misc i915 fixes all over the place.

* tag 'drm-intel-next-fixes-2016-01-14' of git://anongit.freedesktop.org/drm-intel:
  drm/i915/gen9: Set PIN_ZONE_4G end to 4GB - 1 page
  drm/i915: Widen return value for reservation_object_wait_timeout_rcu to long.
  drm/i915: intel_hpd_init(): Fix suspend/resume reprobing
  drm/i915: shut up gen8+ SDE irq dmesg noise, again
  drm/i915: Restore inhibiting the load of the default context
  drm/i915: Tune down rpm wakelock debug checks
  drm/i915: Avoid writing relocs with addresses in non-canonical form
  drm/i915: Move Braswell stop_machine GGTT insertion workaround

8 files changed, 108 insertions, 41 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6c60e04..ddc21d4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3488,7 +3488,7 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 	if (flags & PIN_MAPPABLE)
 		end = min_t(u64, end, dev_priv->gtt.mappable_end);
 	if (flags & PIN_ZONE_4G)
-		end = min_t(u64, end, (1ULL << 32));
+		end = min_t(u64, end, (1ULL << 32) - PAGE_SIZE);
 
 	if (alignment == 0)
 		alignment = flags & PIN_MAPPABLE ? fence_alignment :
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 900ffd0..c25083c 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -347,6 +347,10 @@ void i915_gem_context_reset(struct drm_device *dev)
 			i915_gem_context_unreference(lctx);
 			ring->last_context = NULL;
 		}
+
+		/* Force the GPU state to be reinitialised on enabling */
+		if (ring->default_context)
+			ring->default_context->legacy_hw_ctx.initialized = false;
 	}
 }
 
@@ -715,7 +719,7 @@ static int do_switch(struct drm_i915_gem_request *req)
 	if (ret)
 		goto unpin_out;
 
-	if (!to->legacy_hw_ctx.initialized) {
+	if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to)) {
 		hw_flags |= MI_RESTORE_INHIBIT;
 		/* NB: If we inhibit the restore, the context is not allowed to
 		 * die because future work may end up depending on valid address
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 5d01ea6..dccb517 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -249,6 +249,31 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 		obj->cache_level != I915_CACHE_NONE);
 }
 
+/* Used to convert any address to canonical form.
+ * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
+ * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
+ * addresses to be in a canonical form:
+ * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
+ * canonical form [63:48] == [47]."
+ */
+#define GEN8_HIGH_ADDRESS_BIT 47
+static inline uint64_t gen8_canonical_addr(uint64_t address)
+{
+	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
+}
+
+static inline uint64_t gen8_noncanonical_addr(uint64_t address)
+{
+	return address & ((1ULL << (GEN8_HIGH_ADDRESS_BIT + 1)) - 1);
+}
+
+static inline uint64_t
+relocation_target(struct drm_i915_gem_relocation_entry *reloc,
+		  uint64_t target_offset)
+{
+	return gen8_canonical_addr((int)reloc->delta + target_offset);
+}
+
 static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
 		   struct drm_i915_gem_relocation_entry *reloc,
@@ -256,7 +281,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
-	uint64_t delta = reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	char *vaddr;
 	int ret;
 
@@ -292,7 +317,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint64_t delta = reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	uint64_t offset;
 	void __iomem *reloc_page;
 	int ret;
@@ -347,7 +372,7 @@ relocate_entry_clflush(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
-	uint64_t delta = (int)reloc->delta + target_offset;
+	uint64_t delta = relocation_target(reloc, target_offset);
 	char *vaddr;
 	int ret;
 
@@ -395,7 +420,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	target_i915_obj = target_vma->obj;
 	target_obj = &target_vma->obj->base;
 
-	target_offset = target_vma->node.start;
+	target_offset = gen8_canonical_addr(target_vma->node.start);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -994,6 +1019,21 @@ validate_exec_list(struct drm_device *dev,
 		if (exec[i].flags & invalid_flags)
 			return -EINVAL;
 
+		/* Offset can be used as input (EXEC_OBJECT_PINNED), reject
+		 * any non-page-aligned or non-canonical addresses.
+		 */
+		if (exec[i].flags & EXEC_OBJECT_PINNED) {
+			if (exec[i].offset !=
+			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
+				return -EINVAL;
+
+			/* From drm_mm perspective address space is continuous,
+			 * so from this point we're always using non-canonical
+			 * form internally.
+			 */
+			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+		}
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
@@ -1687,6 +1727,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++) {
+			exec2_list[i].offset =
+				gen8_canonical_addr(exec2_list[i].offset);
 			ret = __copy_to_user(&user_exec_list[i].offset,
 					     &exec2_list[i].offset,
 					     sizeof(user_exec_list[i].offset));
@@ -1752,6 +1794,8 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		int i;
 
 		for (i = 0; i < args->buffer_count; i++) {
+			exec2_list[i].offset =
+				gen8_canonical_addr(exec2_list[i].offset);
 			ret = __copy_to_user(&user_exec_list[i].offset,
 					     &exec2_list[i].offset,
 					     sizeof(user_exec_list[i].offset));
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 52bc6c3..56f4f2e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2384,6 +2384,32 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	assert_rpm_atomic_end(dev_priv, rpm_atomic_seq);
 }
 
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct sg_table *st;
+	uint64_t start;
+	enum i915_cache_level level;
+	u32 flags;
+};
+
+static int gen8_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+	gen8_ggtt_insert_entries(arg->vm, arg->st,
+				 arg->start, arg->level, arg->flags);
+	return 0;
+}
+
+static void gen8_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					  struct sg_table *st,
+					  uint64_t start,
+					  enum i915_cache_level level,
+					  u32 flags)
+{
+	struct insert_entries arg = { vm, st, start, level, flags };
+	stop_machine(gen8_ggtt_insert_entries__cb, &arg, NULL);
+}
+
 /*
  * Binds an object into the global gtt with the specified cache level. The object
  * will be accessible to the GPU via commands whose operands reference offsets
@@ -2560,26 +2586,6 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	return 0;
 }
 
-struct ggtt_bind_vma__cb {
-	struct i915_vma *vma;
-	enum i915_cache_level cache_level;
-	u32 flags;
-};
-
-static int ggtt_bind_vma__cb(void *_arg)
-{
-	struct ggtt_bind_vma__cb *arg = _arg;
-	return ggtt_bind_vma(arg->vma, arg->cache_level, arg->flags);
-}
-
-static int ggtt_bind_vma__BKL(struct i915_vma *vma,
-			      enum i915_cache_level cache_level,
-			      u32 flags)
-{
-	struct ggtt_bind_vma__cb arg = { vma, cache_level, flags };
-	return stop_machine(ggtt_bind_vma__cb, &arg, NULL);
-}
-
 static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 				 enum i915_cache_level cache_level,
 				 u32 flags)
@@ -3048,8 +3054,8 @@ static int gen8_gmch_probe(struct drm_device *dev,
 	dev_priv->gtt.base.bind_vma = ggtt_bind_vma;
 	dev_priv->gtt.base.unbind_vma = ggtt_unbind_vma;
 
-	if (IS_CHERRYVIEW(dev))
-		dev_priv->gtt.base.bind_vma = ggtt_bind_vma__BKL;
+	if (IS_CHERRYVIEW(dev_priv))
+		dev_priv->gtt.base.insert_entries = gen8_ggtt_insert_entries__BKL;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3f8c753..fa8afa7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2414,9 +2414,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 				spt_irq_handler(dev, pch_iir);
 			else
 				cpt_irq_handler(dev, pch_iir);
-		} else
-			DRM_ERROR("The master control interrupt lied (SDE)!\n");
-
+		} else {
+			/*
+			 * Like on previous PCH there seems to be something
+			 * fishy going on with forwarding PCH interrupts.
+			 */
+			DRM_DEBUG_DRIVER("The master control interrupt lied (SDE)!\n");
+		}
 	}
 
 	I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index ceaea7a..580d094 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13763,13 +13763,15 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 	/* For framebuffer backed by dmabuf, wait for fence */
 	if (obj && obj->base.dma_buf) {
-		ret = reservation_object_wait_timeout_rcu(obj->base.dma_buf->resv,
-							  false, true,
-							  MAX_SCHEDULE_TIMEOUT);
-		if (ret == -ERESTARTSYS)
-			return ret;
+		long lret;
+
+		lret = reservation_object_wait_timeout_rcu(obj->base.dma_buf->resv,
+							   false, true,
+							   MAX_SCHEDULE_TIMEOUT);
+		if (lret == -ERESTARTSYS)
+			return lret;
 
-		WARN_ON(ret < 0);
+		WARN(lret < 0, "waiting returns %li\n", lret);
 	}
 
 	if (!obj) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d523ebb..ea54158 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1442,8 +1442,10 @@ static inline void
 assert_rpm_wakelock_held(struct drm_i915_private *dev_priv)
 {
 	assert_rpm_device_not_suspended(dev_priv);
-	WARN_ONCE(!atomic_read(&dev_priv->pm.wakeref_count),
-		  "RPM wakelock ref not held during HW access");
+	/* FIXME: Needs to be converted back to WARN_ONCE, but currently causes
+	 * too much noise. */
+	if (!atomic_read(&dev_priv->pm.wakeref_count))
+		DRM_DEBUG_DRIVER("RPM wakelock ref not held during HW access");
 }
 
 static inline int
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index a294a3c..bee6730 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -468,9 +468,14 @@ void intel_hpd_init(struct drm_i915_private *dev_priv)
 	list_for_each_entry(connector, &mode_config->connector_list, head) {
 		struct intel_connector *intel_connector = to_intel_connector(connector);
 		connector->polled = intel_connector->polled;
-		if (connector->encoder && !connector->polled && I915_HAS_HOTPLUG(dev) && intel_connector->encoder->hpd_pin > HPD_NONE)
-			connector->polled = DRM_CONNECTOR_POLL_HPD;
+
+		/* MST has a dynamic intel_connector->encoder and it's reprobing
+		 * is all handled by the MST helpers. */
 		if (intel_connector->mst_port)
+			continue;
+
+		if (!connector->polled && I915_HAS_HOTPLUG(dev) &&
+		    intel_connector->encoder->hpd_pin > HPD_NONE)
 			connector->polled = DRM_CONNECTOR_POLL_HPD;
 	}