Am 02.04.19 um 20:12 schrieb Liu, Shaoyun:
On XGMI configuration the ib test may tooks longer to finish
Change-Id: If3afd8eac3c342d32c387804b51fc4a4bdd35d35
Signed-off-by: shaoyunl <shaoyun.liu@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 0b8ef2d..45f251f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -346,6 +346,9 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
}
+ if (adev->gmc.xgmi.hive_id)
+ tmo_gfx = 2 * AMDGPU_IB_TEST_TIMEOUT;
+
Probably better to use an "else if" to note that those two mutual exclusive.
Additional to that I think it is time now to add
AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT define instead of just abusing the
existing one over and over again (same of course for the SRIOV case).
Christian.
for (i = 0; i < adev->num_rings; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
long tmo;
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
