drm/amdgpu: add ring soft recovery v4

Instead of hammering hard on the GPU try a soft recovery first.

v2: reorder code a bit
v3: increase timeout to 10ms, increment GPU reset counter
v4: squash in compile fix (Christian)

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>

1 files changed, 25 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 5dfd26be1eec..b70e85ec147d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -383,6 +383,31 @@ void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
         amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
 }
 
+/**
+ * amdgpu_ring_soft_recovery - try to soft recover a ring lockup
+ *
+ * @ring: ring to try the recovery on
+ * @vmid: VMID we try to get going again
+ * @fence: timedout fence
+ *
+ * Tries to get a ring proceeding again when it is stuck.
+ */
+bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
+                               struct dma_fence *fence)
+{
+        ktime_t deadline = ktime_add_us(ktime_get(), 10000);
+
+        if (!ring->funcs->soft_recovery)
+                return false;
+
+        atomic_inc(&ring->adev->gpu_reset_counter);
+        while (!dma_fence_is_signaled(fence) &&
+               ktime_to_ns(ktime_sub(deadline, ktime_get())) > 0)
+                ring->funcs->soft_recovery(ring, vmid);
+
+        return dma_fence_is_signaled(fence);
+}
+
 /*
  * Debugfs info
  */