3 files changed, 30 insertions, 9 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 638540943c61..c94cce96544c 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -146,7 +146,7 @@ vc4_save_hang_state(struct drm_device *dev)
 	struct vc4_exec_info *exec[2];
 	struct vc4_bo *bo;
 	unsigned long irqflags;
-	unsigned int i, j, unref_list_count, prev_idx;
+	unsigned int i, j, k, unref_list_count;
 
 	kernel_state = kcalloc(1, sizeof(*kernel_state), GFP_KERNEL);
 	if (!kernel_state)
@@ -182,7 +182,7 @@ vc4_save_hang_state(struct drm_device *dev)
 		return;
 	}
 
-	prev_idx = 0;
+	k = 0;
 	for (i = 0; i < 2; i++) {
 		if (!exec[i])
 			continue;
@@ -197,7 +197,7 @@ vc4_save_hang_state(struct drm_device *dev)
 			WARN_ON(!refcount_read(&bo->usecnt));
 			refcount_inc(&bo->usecnt);
 			drm_gem_object_get(&exec[i]->bo[j]->base);
-			kernel_state->bo[j + prev_idx] = &exec[i]->bo[j]->base;
+			kernel_state->bo[k++] = &exec[i]->bo[j]->base;
 		}
 
 		list_for_each_entry(bo, &exec[i]->unref_list, unref_head) {
@@ -205,12 +205,12 @@ vc4_save_hang_state(struct drm_device *dev)
 			 * because they are naturally unpurgeable.
 			 */
 			drm_gem_object_get(&bo->base.base);
-			kernel_state->bo[j + prev_idx] = &bo->base.base;
-			j++;
+			kernel_state->bo[k++] = &bo->base.base;
 		}
-		prev_idx = j + 1;
 	}
 
+	WARN_ON_ONCE(k != state->bo_count);
+
 	if (exec[0])
 		state->start_bin = exec[0]->ct0ca;
 	if (exec[1])
@@ -436,6 +436,19 @@ vc4_flush_caches(struct drm_device *dev)
 		  VC4_SET_FIELD(0xf, V3D_SLCACTL_ICC));
 }
 
+static void
+vc4_flush_texture_caches(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	V3D_WRITE(V3D_L2CACTL,
+		  V3D_L2CACTL_L2CCLR);
+
+	V3D_WRITE(V3D_SLCACTL,
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T1CC) |
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T0CC));
+}
+
 /* Sets the registers for the next job to be actually be executed in
  * the hardware.
  *
@@ -474,6 +487,14 @@ vc4_submit_next_render_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	/* A previous RCL may have written to one of our textures, and
+	 * our full cache flush at bin time may have occurred before
+	 * that RCL completed.  Flush the texture cache now, but not
+	 * the instructions or uniforms (since we don't write those
+	 * from an RCL).
+	 */
+	vc4_flush_texture_caches(dev);
+
 	submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 26eddbb62893..3dd62d75f531 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -209,9 +209,6 @@ vc4_irq_postinstall(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
-	/* Undo the effects of a previous vc4_irq_uninstall. */
-	enable_irq(dev->irq);
-
 	/* Enable both the render done and out of memory interrupts. */
 	V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS);
 
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 622cd43840b8..493f392b3a0a 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -327,6 +327,9 @@ static int vc4_v3d_runtime_resume(struct device *dev)
 		return ret;
 
 	vc4_v3d_init_hw(vc4->dev);
+
+	/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
+	enable_irq(vc4->dev->irq);
 	vc4_irq_postinstall(vc4->dev);
 
 	return 0;