summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/r520.c
diff options
context:
space:
mode:
authorJerome Glisse <jglisse@redhat.com>2010-01-07 14:39:21 +0300
committerDave Airlie <airlied@redhat.com>2010-01-08 06:09:59 +0300
commitcafe6609d6dc0a6a278f9fdbb59ce4d761a35ddd (patch)
treea3e15eabffd6e10bed1ef639fc2f2e087c67b047 /drivers/gpu/drm/radeon/r520.c
parent62cdc0c20663ef840a94850892517b2b7f584904 (diff)
downloadlinux-cafe6609d6dc0a6a278f9fdbb59ce4d761a35ddd.tar.xz
drm/radeon/kms: Schedule host path read cache flush through the ring V2
R300 family will hard lockup if host path read cache flush is done through MMIO to HOST_PATH_CNTL. But scheduling same flush through ring seems harmless. This patch remove the hdp_flush callback and add a flush after each fence emission which means a flush after each IB schedule. Thus we should have same behavior without the hard lockup. Tested on R100,R200,R300,R400,R500,R600,R700 family. V2: Adjust fence counts in r600_blit_prepare_copy() Signed-off-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'drivers/gpu/drm/radeon/r520.c')
-rw-r--r--drivers/gpu/drm/radeon/r520.c1
1 files changed, 1 insertions, 0 deletions
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index 0f3843b6dac7..9a189072f2b9 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -186,6 +186,7 @@ static int r520_startup(struct radeon_device *rdev)
}
/* Enable IRQ */
rs600_irq_set(rdev);
+ rdev->config.r300.hdp_cntl = RREG32(RADEON_HOST_PATH_CNTL);
/* 1M ring buffer */
r = r100_cp_init(rdev, 1024 * 1024);
if (r) {