Merge tag 'drm-vc4-next-2016-03-14' of github.com:anholt/linux into drm-next

This pull request covers what's left for 4.6. Notably, it includes a
significant 3D performance improvement and a fix to HDMI hotplug
detection for the Pi2/3.

* tag 'drm-vc4-next-2016-03-14' of github.com:anholt/linux:
drm/vc4: Recognize a more specific compatible string for V3D.
dt-bindings: Add binding docs for V3D.
drm/vc4: Return -EFAULT on copy_from_user() failure
drm/vc4: Respect GPIO_ACTIVE_LOW on HDMI HPD if set in the devicetree.
drm/vc4: Let gpiolib know that we're OK with sleeping for HPD.
drm/vc4: improve throughput by pipelining binning and rendering jobs

Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt

···
 		  as an interrupt/status bit in the HDMI controller
 		  itself).  See bindings/pinctrl/brcm,bcm2835-gpio.txt
 
+Required properties for V3D:
+- compatible:	Should be "brcm,bcm2835-v3d"
+- reg:		Physical base address and length of the V3D's registers
+- interrupts:	The interrupt number
+		  See bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+
 Example:
 pixelvalve@7e807000 {
 	compatible = "brcm,bcm2835-pixelvalve2";
···
 	clocks = <&clocks BCM2835_PLLH_PIX>,
 		 <&clocks BCM2835_CLOCK_HSM>;
 	clock-names = "pixel", "hdmi";
+};
+
+v3d: v3d@7ec00000 {
+	compatible = "brcm,bcm2835-v3d";
+	reg = <0x7ec00000 0x1000>;
+	interrupts = <1 10>;
 };
 
 vc4: gpu {

drivers/gpu/drm/vc4/vc4_bo.c

···
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
-	ret = copy_from_user(bo->base.vaddr,
+	if (copy_from_user(bo->base.vaddr,
 			     (void __user *)(uintptr_t)args->data,
-			     args->size);
-	if (ret != 0)
+			     args->size)) {
+		ret = -EFAULT;
 		goto fail;
+	}
 	/* Clear the rest of the memory from allocating from the BO
 	 * cache.
 	 */

drivers/gpu/drm/vc4/vc4_drv.h

···
 	/* Protects bo_cache and the BO stats. */
 	struct mutex bo_lock;
 
-	/* Sequence number for the last job queued in job_list.
+	/* Sequence number for the last job queued in bin_job_list.
 	 * Starts at 0 (no jobs emitted).
 	 */
 	uint64_t emit_seqno;
···
 	 */
 	uint64_t finished_seqno;
 
-	/* List of all struct vc4_exec_info for jobs to be executed.
-	 * The first job in the list is the one currently programmed
-	 * into ct0ca/ct1ca for execution.
+	/* List of all struct vc4_exec_info for jobs to be executed in
+	 * the binner.  The first job in the list is the one currently
+	 * programmed into ct0ca for execution.
 	 */
-	struct list_head job_list;
+	struct list_head bin_job_list;
+
+	/* List of all struct vc4_exec_info for jobs that have
+	 * completed binning and are ready for rendering.  The first
+	 * job in the list is the one currently programmed into ct1ca
+	 * for execution.
+	 */
+	struct list_head render_job_list;
+
 	/* List of the finished vc4_exec_infos waiting to be freed by
 	 * job_done_work.
 	 */
···
 };
 
 static inline struct vc4_exec_info *
-vc4_first_job(struct vc4_dev *vc4)
+vc4_first_bin_job(struct vc4_dev *vc4)
 {
-	if (list_empty(&vc4->job_list))
+	if (list_empty(&vc4->bin_job_list))
 		return NULL;
-	return list_first_entry(&vc4->job_list, struct vc4_exec_info, head);
+	return list_first_entry(&vc4->bin_job_list, struct vc4_exec_info, head);
+}
+
+static inline struct vc4_exec_info *
+vc4_first_render_job(struct vc4_dev *vc4)
+{
+	if (list_empty(&vc4->render_job_list))
+		return NULL;
+	return list_first_entry(&vc4->render_job_list,
+				struct vc4_exec_info, head);
 }
 
 /**
···
 			 struct drm_file *file_priv);
 int vc4_wait_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
-void vc4_submit_next_job(struct drm_device *dev);
+void vc4_submit_next_bin_job(struct drm_device *dev);
+void vc4_submit_next_render_job(struct drm_device *dev);
+void vc4_move_job_to_render(struct drm_device *dev, struct vc4_exec_info *exec);
 int vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno,
 		       uint64_t timeout_ns, bool interruptible);
 void vc4_job_handle_completed(struct vc4_dev *vc4);

drivers/gpu/drm/vc4/vc4_gem.c

···
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_get_hang_state *state;
 	struct vc4_hang_state *kernel_state;
-	struct vc4_exec_info *exec;
+	struct vc4_exec_info *exec[2];
 	struct vc4_bo *bo;
 	unsigned long irqflags;
-	unsigned int i, unref_list_count;
+	unsigned int i, j, unref_list_count, prev_idx;
 
 	kernel_state = kcalloc(1, sizeof(*kernel_state), GFP_KERNEL);
 	if (!kernel_state)
···
 	state = &kernel_state->user_state;
 
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
-	exec = vc4_first_job(vc4);
-	if (!exec) {
+	exec[0] = vc4_first_bin_job(vc4);
+	exec[1] = vc4_first_render_job(vc4);
+	if (!exec[0] && !exec[1]) {
 		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		return;
 	}
 
-	unref_list_count = 0;
-	list_for_each_entry(bo, &exec->unref_list, unref_head)
-		unref_list_count++;
+	/* Get the bos from both binner and renderer into hang state. */
+	state->bo_count = 0;
+	for (i = 0; i < 2; i++) {
+		if (!exec[i])
+			continue;
 
-	state->bo_count = exec->bo_count + unref_list_count;
-	kernel_state->bo = kcalloc(state->bo_count, sizeof(*kernel_state->bo),
-				   GFP_ATOMIC);
+		unref_list_count = 0;
+		list_for_each_entry(bo, &exec[i]->unref_list, unref_head)
+			unref_list_count++;
+		state->bo_count += exec[i]->bo_count + unref_list_count;
+	}
+
+	kernel_state->bo = kcalloc(state->bo_count,
+				   sizeof(*kernel_state->bo), GFP_ATOMIC);
+
 	if (!kernel_state->bo) {
 		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		return;
 	}
 
-	for (i = 0; i < exec->bo_count; i++) {
-		drm_gem_object_reference(&exec->bo[i]->base);
-		kernel_state->bo[i] = &exec->bo[i]->base;
+	prev_idx = 0;
+	for (i = 0; i < 2; i++) {
+		if (!exec[i])
+			continue;
+
+		for (j = 0; j < exec[i]->bo_count; j++) {
+			drm_gem_object_reference(&exec[i]->bo[j]->base);
+			kernel_state->bo[j + prev_idx] = &exec[i]->bo[j]->base;
+		}
+
+		list_for_each_entry(bo, &exec[i]->unref_list, unref_head) {
+			drm_gem_object_reference(&bo->base.base);
+			kernel_state->bo[j + prev_idx] = &bo->base.base;
+			j++;
+		}
+		prev_idx = j + 1;
 	}
 
-	list_for_each_entry(bo, &exec->unref_list, unref_head) {
-		drm_gem_object_reference(&bo->base.base);
-		kernel_state->bo[i] = &bo->base.base;
-		i++;
-	}
-
-	state->start_bin = exec->ct0ca;
-	state->start_render = exec->ct1ca;
+	if (exec[0])
+		state->start_bin = exec[0]->ct0ca;
+	if (exec[1])
+		state->start_render = exec[1]->ct1ca;
 
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 
···
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint32_t ct0ca, ct1ca;
 	unsigned long irqflags;
-	struct vc4_exec_info *exec;
+	struct vc4_exec_info *bin_exec, *render_exec;
 
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
-	exec = vc4_first_job(vc4);
+
+	bin_exec = vc4_first_bin_job(vc4);
+	render_exec = vc4_first_render_job(vc4);
 
 	/* If idle, we can stop watching for hangs. */
-	if (!exec) {
+	if (!bin_exec && !render_exec) {
 		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		return;
 	}
···
 	/* If we've made any progress in execution, rearm the timer
 	 * and wait.
 	 */
-	if (ct0ca != exec->last_ct0ca || ct1ca != exec->last_ct1ca) {
-		exec->last_ct0ca = ct0ca;
-		exec->last_ct1ca = ct1ca;
+	if ((bin_exec && ct0ca != bin_exec->last_ct0ca) ||
+	    (render_exec && ct1ca != render_exec->last_ct1ca)) {
+		if (bin_exec)
+			bin_exec->last_ct0ca = ct0ca;
+		if (render_exec)
+			render_exec->last_ct1ca = ct1ca;
 		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		vc4_queue_hangcheck(dev);
 		return;
···
  * The job_lock should be held during this.
  */
 void
-vc4_submit_next_job(struct drm_device *dev)
+vc4_submit_next_bin_job(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct vc4_exec_info *exec = vc4_first_job(vc4);
+	struct vc4_exec_info *exec;
 
+again:
+	exec = vc4_first_bin_job(vc4);
 	if (!exec)
 		return;
 
···
 	V3D_WRITE(V3D_BPOA, 0);
 	V3D_WRITE(V3D_BPOS, 0);
 
-	if (exec->ct0ca != exec->ct0ea)
+	/* Either put the job in the binner if it uses the binner, or
+	 * immediately move it to the to-be-rendered queue.
+	 */
+	if (exec->ct0ca != exec->ct0ea) {
 		submit_cl(dev, 0, exec->ct0ca, exec->ct0ea);
+	} else {
+		vc4_move_job_to_render(dev, exec);
+		goto again;
+	}
+}
+
+void
+vc4_submit_next_render_job(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_exec_info *exec = vc4_first_render_job(vc4);
+
+	if (!exec)
+		return;
+
 	submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
+}
+
+void
+vc4_move_job_to_render(struct drm_device *dev, struct vc4_exec_info *exec)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	bool was_empty = list_empty(&vc4->render_job_list);
+
+	list_move_tail(&exec->head, &vc4->render_job_list);
+	if (was_empty)
+		vc4_submit_next_render_job(dev);
 }
 
 static void
···
 	exec->seqno = seqno;
 	vc4_update_bo_seqnos(exec, seqno);
 
-	list_add_tail(&exec->head, &vc4->job_list);
+	list_add_tail(&exec->head, &vc4->bin_job_list);
 
 	/* If no job was executing, kick ours off.  Otherwise, it'll
-	 * get started when the previous job's frame done interrupt
+	 * get started when the previous job's flush done interrupt
 	 * occurs.
 	 */
-	if (vc4_first_job(vc4) == exec) {
-		vc4_submit_next_job(dev);
+	if (vc4_first_bin_job(vc4) == exec) {
+		vc4_submit_next_bin_job(dev);
 		vc4_queue_hangcheck(dev);
 	}
 
···
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
-	INIT_LIST_HEAD(&vc4->job_list);
+	INIT_LIST_HEAD(&vc4->bin_job_list);
+	INIT_LIST_HEAD(&vc4->render_job_list);
 	INIT_LIST_HEAD(&vc4->job_done_list);
 	INIT_LIST_HEAD(&vc4->seqno_cb_list);
 	spin_lock_init(&vc4->job_lock);

drivers/gpu/drm/vc4/vc4_hdmi.c

···
 	void __iomem *hdmicore_regs;
 	void __iomem *hd_regs;
 	int hpd_gpio;
+	bool hpd_active_low;
 
 	struct clk *pixel_clock;
 	struct clk *hsm_clock;
···
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
 	if (vc4->hdmi->hpd_gpio) {
-		if (gpio_get_value(vc4->hdmi->hpd_gpio))
+		if (gpio_get_value_cansleep(vc4->hdmi->hpd_gpio) ^
+		    vc4->hdmi->hpd_active_low)
 			return connector_status_connected;
 		else
 			return connector_status_disconnected;
···
 	 * we'll use the HDMI core's register.
 	 */
 	if (of_find_property(dev->of_node, "hpd-gpios", &value)) {
-		hdmi->hpd_gpio = of_get_named_gpio(dev->of_node, "hpd-gpios", 0);
+		enum of_gpio_flags hpd_gpio_flags;
+
+		hdmi->hpd_gpio = of_get_named_gpio_flags(dev->of_node,
+							 "hpd-gpios", 0,
+							 &hpd_gpio_flags);
 		if (hdmi->hpd_gpio < 0) {
 			ret = hdmi->hpd_gpio;
 			goto err_unprepare_hsm;
 		}
+
+		hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW;
 	}
 
 	vc4->hdmi = hdmi;

drivers/gpu/drm/vc4/vc4_irq.c

···
  * disables that specific interrupt, and 0s written are ignored
  * (reading either one returns the set of enabled interrupts).
  *
+ * When we take a binning flush done interrupt, we need to submit the
+ * next frame for binning and move the finished frame to the render
+ * thread.
+ *
  * When we take a render frame interrupt, we need to wake the
  * processes waiting for some frame to be done, and get the next frame
  * submitted ASAP (so the hardware doesn't sit idle when there's work
···
 #include "vc4_regs.h"
 
 #define V3D_DRIVER_IRQS (V3D_INT_OUTOMEM | \
+			 V3D_INT_FLDONE | \
 			 V3D_INT_FRDONE)
 
 DECLARE_WAIT_QUEUE_HEAD(render_wait);
···
 		unsigned long irqflags;
 
 		spin_lock_irqsave(&vc4->job_lock, irqflags);
-		current_exec = vc4_first_job(vc4);
+		current_exec = vc4_first_bin_job(vc4);
 		if (current_exec) {
 			vc4->overflow_mem->seqno = vc4->finished_seqno + 1;
 			list_add_tail(&vc4->overflow_mem->unref_head,
···
 }
 
 static void
-vc4_irq_finish_job(struct drm_device *dev)
+vc4_irq_finish_bin_job(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct vc4_exec_info *exec = vc4_first_job(vc4);
+	struct vc4_exec_info *exec = vc4_first_bin_job(vc4);
+
+	if (!exec)
+		return;
+
+	vc4_move_job_to_render(dev, exec);
+	vc4_submit_next_bin_job(dev);
+}
+
+static void
+vc4_cancel_bin_job(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_exec_info *exec = vc4_first_bin_job(vc4);
+
+	if (!exec)
+		return;
+
+	list_move_tail(&exec->head, &vc4->bin_job_list);
+	vc4_submit_next_bin_job(dev);
+}
+
+static void
+vc4_irq_finish_render_job(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_exec_info *exec = vc4_first_render_job(vc4);
 
 	if (!exec)
 		return;
 
 	vc4->finished_seqno++;
 	list_move_tail(&exec->head, &vc4->job_done_list);
-	vc4_submit_next_job(dev);
+	vc4_submit_next_render_job(dev);
 
 	wake_up_all(&vc4->job_wait_queue);
 	schedule_work(&vc4->job_done_work);
···
 	barrier();
 	intctl = V3D_READ(V3D_INTCTL);
 
-	/* Acknowledge the interrupts we're handling here. The render
-	 * frame done interrupt will be cleared, while OUTOMEM will
-	 * stay high until the underlying cause is cleared.
+	/* Acknowledge the interrupts we're handling here. The binner
+	 * last flush / render frame done interrupt will be cleared,
+	 * while OUTOMEM will stay high until the underlying cause is
+	 * cleared.
 	 */
 	V3D_WRITE(V3D_INTCTL, intctl);
 
···
 		status = IRQ_HANDLED;
 	}
 
+	if (intctl & V3D_INT_FLDONE) {
+		spin_lock(&vc4->job_lock);
+		vc4_irq_finish_bin_job(dev);
+		spin_unlock(&vc4->job_lock);
+		status = IRQ_HANDLED;
+	}
+
 	if (intctl & V3D_INT_FRDONE) {
 		spin_lock(&vc4->job_lock);
-		vc4_irq_finish_job(dev);
+		vc4_irq_finish_render_job(dev);
 		spin_unlock(&vc4->job_lock);
 		status = IRQ_HANDLED;
 	}
···
 	V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS);
 
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
-	vc4_irq_finish_job(dev);
+	vc4_cancel_bin_job(dev);
+	vc4_irq_finish_render_job(dev);
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 }

drivers/gpu/drm/vc4/vc4_v3d.c

···
 }
 
 static const struct of_device_id vc4_v3d_dt_match[] = {
+	{ .compatible = "brcm,bcm2835-v3d" },
 	{ .compatible = "brcm,vc4-v3d" },
 	{}
 };