Am 17.10.23 um 16:36 schrieb Stanley.Yang:
This is workaround, kiq ring test failed in suspend stage when do ras
recovery for gfx v9_4_3.
Any idea why that failed? Problems like this usually point to an
incorrect init or in this case re-init procedure and are actually what
the ring test should uncover.
Christian.
Change-Id: I8de9900aa76706f59bc029d4e9e8438c6e1db8e0
Signed-off-by: Stanley.Yang <Stanley.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 9a158018ae16..902e60203809 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -29,6 +29,7 @@
#include "amdgpu_rlc.h"
#include "amdgpu_ras.h"
#include "amdgpu_xcp.h"
+#include "amdgpu_xgmi.h"
/* delay 0.1 second to enable gfx off feature */
#define GFX_OFF_DELAY_ENABLE msecs_to_jiffies(100)
@@ -501,6 +502,9 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
{
struct amdgpu_kiq *kiq = &adev->gfx.kiq[xcc_id];
struct amdgpu_ring *kiq_ring = &kiq->ring;
+ struct amdgpu_hive_info *hive;
+ struct amdgpu_ras *ras;
+ int hive_ras_recovery;
int i, r = 0;
int j;
@@ -521,6 +525,23 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
RESET_QUEUES, 0, 0);
}
+ /**
+ * This is workaround: only skip kiq_ring test
+ * during ras recovery in suspend stage for gfx v9_4_3
+ */
+ hive = amdgpu_get_xgmi_hive(adev);
+ if (hive) {
+ hive_ras_recovery = atomic_read(&hive->ras_recovery);
+ amdgpu_put_xgmi_hive(hive);
+ }
+
+ ras = amdgpu_ras_get_context(adev);
+ if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) &&
+ ras && (atomic_read(&ras->in_recovery) || hive_ras_recovery)) {
+ spin_unlock(&kiq->ring_lock);
+ return 0;
+ }
+
if (kiq_ring->sched.ready && !adev->job_hang)
r = amdgpu_ring_test_helper(kiq_ring);
spin_unlock(&kiq->ring_lock);
