[PATCH] drm/radeon: flush read cache for gtt with fence on r6xx and newer GPU V2

[j.glisse@gmail.com]

From: Jerome Glisse <jglisse@redhat.com>

Cayman seems to be particularly sensitive to read cache returning
old data after bind/unbind to GTT. Flush read cache for GTT range
with each fences for all new hw. Should fix several rendering glitches.
Like

V2 flush whole address space

https://bugs.freedesktop.org/show_bug.cgi?id=40221
https://bugs.freedesktop.org/show_bug.cgi?id=38022
https://bugzilla.redhat.com/show_bug.cgi?id=738790

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
---
 drivers/gpu/drm/radeon/evergreen_blit_kms.c |    4 ++--
 drivers/gpu/drm/radeon/r600.c               |   12 ++++++++++++
 drivers/gpu/drm/radeon/r600_blit_kms.c      |    4 ++--
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index dcf11bb..e9aeeed 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -613,9 +613,9 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
 	rdev->r600_blit.ring_size_common = 55; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 10; /* fence emit for VB IB */
+	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
-	rdev->r600_blit.ring_size_common += 10; /* fence emit for done copy */
+	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
 
 	rdev->r600_blit.ring_size_per_loop = 74;
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 12470b0..983808a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2331,6 +2331,12 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 	if (rdev->wb.use_event) {
 		u64 addr = rdev->wb.gpu_addr + R600_WB_EVENT_OFFSET +
 			(u64)(rdev->fence_drv.scratch_reg - rdev->scratch.reg_base);
+		/* flush read cache over gart */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SURFACE_SYNC, 3));
+		radeon_ring_write(rdev, PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA);
+		radeon_ring_write(rdev, 0xFFFFFFFF);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, 10); /* poll interval */
 		/* EVENT_WRITE_EOP - flush caches, send int */
 		radeon_ring_write(rdev, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 		radeon_ring_write(rdev, EVENT_TYPE(CACHE_FLUSH_AND_INV_EVENT_TS) | EVENT_INDEX(5));
@@ -2339,6 +2345,12 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 		radeon_ring_write(rdev, fence->seq);
 		radeon_ring_write(rdev, 0);
 	} else {
+		/* flush read cache over gart */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SURFACE_SYNC, 3));
+		radeon_ring_write(rdev, PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA);
+		radeon_ring_write(rdev, 0xFFFFFFFF);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, 10); /* poll interval */
 		radeon_ring_write(rdev, PACKET3(PACKET3_EVENT_WRITE, 0));
 		radeon_ring_write(rdev, EVENT_TYPE(CACHE_FLUSH_AND_INV_EVENT) | EVENT_INDEX(0));
 		/* wait for 3D idle clean */
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index c4cf130..36e62f2 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -500,9 +500,9 @@ int r600_blit_init(struct radeon_device *rdev)
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
 	rdev->r600_blit.ring_size_common = 40; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 10; /* fence emit for VB IB */
+	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
-	rdev->r600_blit.ring_size_common += 10; /* fence emit for done copy */
+	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
 
 	rdev->r600_blit.ring_size_per_loop = 76;
 	/* set_render_target emits 2 extra dwords on rv6xx */
-- 
1.7.1