From f61145f1a4bd7966aa0b15c5cd3950835b284f55 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Thu, 21 Dec 2017 14:17:22 -0800
Subject: [PATCH] drm/vc4: Flush the caches before the bin jobs, as well.
Git-commit: f61145f1a4bd7966aa0b15c5cd3950835b284f55
Patch-mainline: v4.15
References: bsc#1051510
If the frame samples from a render target that was just written, its
cache flush during the binning step may have occurred before the
previous frame's RCL was completed. Flush the texture caches again
before starting each RCL job to make sure that the sampling of the
previous RCL's output is correct.
Fixes flickering in the top left of 3DMMES Taiji.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: ca26d28bbaa3 ("drm/vc4: improve throughput by pipelining binning and rendering jobs")
Link: https://patchwork.freedesktop.org/patch/msgid/20171221221722.23809-1-eric@anholt.net
Reviewed-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
drivers/gpu/drm/vc4/vc4_gem.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -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_de
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);
}