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>

3 files changed, 35 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index facc0f08d804..34e54d41f5ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -33,6 +33,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
         struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
         struct amdgpu_job *job = to_amdgpu_job(s_job);
 
+        if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+                DRM_ERROR("ring %s timeout, but soft recovered\n",
+                          s_job->sched->name);
+                return;
+        }
+
         DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
                   job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
                   ring->fence_drv.sync_seq);
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
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 409fdd9b9710..9cc239968e40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -168,6 +168,8 @@ struct amdgpu_ring_funcs {
         /* priority functions */
         void (*set_priority) (struct amdgpu_ring *ring,
                               enum drm_sched_priority priority);
+        /* Try to soft recover the ring to make the fence signal */
+        void (*soft_recovery)(struct amdgpu_ring *ring, unsigned vmid);
 };
 
 struct amdgpu_ring {
@@ -260,6 +262,8 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring);
 void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
                                                 uint32_t reg0, uint32_t val0,
                                                 uint32_t reg1, uint32_t val1);
+bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
+                               struct dma_fence *fence);
 
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {