summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/radeon/cik.c
diff options
context:
space:
mode:
authorMatthew Dawson <matthew@mjdsystems.ca>2016-02-08 00:51:12 +0300
committerAlex Deucher <alexander.deucher@amd.com>2016-02-10 22:17:15 +0300
commit04db4caf5c836c211977a54c9218f2cdee14897f (patch)
tree99460f045362a3d7bae6b9d1c64843f85cd19107 /drivers/gpu/drm/radeon/cik.c
parent6e9821b26dd45b4a3e30c4219be2abd802563379 (diff)
downloadlinux-04db4caf5c836c211977a54c9218f2cdee14897f.tar.xz
drm/radeon: Avoid double gpu reset by adding a timeout on IB ring tests.
When the radeon driver resets a gpu, it attempts to test whether all the rings can successfully handle an IB. If these rings fail to respond, the process will wait forever. Another gpu reset can't happen at this point, as the current reset holds a lock required to do so. Instead, make all the IB tests run with a timeout, so the system can attempt to recover in this case. While this doesn't fix the underlying issue with card resets failing, it gives the system a higher chance of recovering. These timeouts have been confirmed to help both a Tathi and Hawaii card recover after a gpu reset. This also adds a new function, radeon_fence_wait_timeout, that behaves like fence_wait_timeout. It is used instead of fence_wait_timeout as it continues to work during a reset. radeon_fence_wait is changed to be implemented using this function. V2: - Changed the timeout to 1s, as the default 10s from radeon_wait_timeout was too long. A timeout of 100ms was tested and found to be too short. - Changed radeon_fence_wait_timeout to behave more like fence_wait_timeout. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Matthew Dawson <matthew@mjdsystems.ca> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/radeon/cik.c')
-rw-r--r--drivers/gpu/drm/radeon/cik.c11
1 files changed, 9 insertions, 2 deletions
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 4c30d8c65558..06001400ce8b 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4219,13 +4219,20 @@ int cik_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
return r;
}
- r = radeon_fence_wait(ib.fence, false);
- if (r) {
+ r = radeon_fence_wait_timeout(ib.fence, false, usecs_to_jiffies(
+ RADEON_USEC_IB_TEST_TIMEOUT));
+ if (r < 0) {
DRM_ERROR("radeon: fence wait failed (%d).\n", r);
radeon_scratch_free(rdev, scratch);
radeon_ib_free(rdev, &ib);
return r;
+ } else if (r == 0) {
+ DRM_ERROR("radeon: fence wait timed out.\n");
+ radeon_scratch_free(rdev, scratch);
+ radeon_ib_free(rdev, &ib);
+ return -ETIMEDOUT;
}
+ r = 0;
for (i = 0; i < rdev->usec_timeout; i++) {
tmp = RREG32(scratch);
if (tmp == 0xDEADBEEF)