drm/amdgpu: add the trailing fence per ring

The trailing fence for ring is used to track the
completion of preemption.
Acked-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -707,22 +707,30 @@ static int amdgpu_debugfs_fence_info(struct seq_file *m, void *data)
 		amdgpu_fence_process(ring);
 
 		seq_printf(m, "--- ring %d (%s) ---\n", i, ring->name);
-		seq_printf(m, "Last signaled fence 0x%08x\n",
+		seq_printf(m, "Last signaled fence          0x%08x\n",
 			   atomic_read(&ring->fence_drv.last_seq));
-		seq_printf(m, "Last emitted        0x%08x\n",
+		seq_printf(m, "Last emitted                 0x%08x\n",
 			   ring->fence_drv.sync_seq);
 
+		if (ring->funcs->type == AMDGPU_RING_TYPE_GFX ||
+		    ring->funcs->type == AMDGPU_RING_TYPE_SDMA) {
+			seq_printf(m, "Last signaled trailing fence 0x%08x\n",
+				   le32_to_cpu(*ring->trail_fence_cpu_addr));
+			seq_printf(m, "Last emitted                 0x%08x\n",
+				   ring->trail_seq);
+		}
+
 		if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 			continue;
 
 		/* set in CP_VMID_PREEMPT and preemption occurred */
-		seq_printf(m, "Last preempted      0x%08x\n",
+		seq_printf(m, "Last preempted               0x%08x\n",
 			   le32_to_cpu(*(ring->fence_drv.cpu_addr + 2)));
 		/* set in CP_VMID_RESET and reset occurred */
-		seq_printf(m, "Last reset          0x%08x\n",
+		seq_printf(m, "Last reset                   0x%08x\n",
 			   le32_to_cpu(*(ring->fence_drv.cpu_addr + 4)));
 		/* Both preemption and reset occurred */
-		seq_printf(m, "Last both           0x%08x\n",
+		seq_printf(m, "Last both                    0x%08x\n",
 			   le32_to_cpu(*(ring->fence_drv.cpu_addr + 6)));
 	}
 	return 0;

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

@@ -281,6 +281,16 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		return r;
 	}
 
+	r = amdgpu_device_wb_get(adev, &ring->trail_fence_offs);
+	if (r) {
+		dev_err(adev->dev,
+			"(%d) ring trail_fence_offs wb alloc failed\n", r);
+		return r;
+	}
+	ring->trail_fence_gpu_addr =
+		adev->wb.gpu_addr + (ring->trail_fence_offs * 4);
+	ring->trail_fence_cpu_addr = &adev->wb.wb[ring->trail_fence_offs];
+
 	r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
 	if (r) {
 		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h

@@ -206,6 +206,10 @@ struct amdgpu_ring {
 	unsigned		fence_offs;
 	uint64_t		current_ctx;
 	char			name[16];
+	u32                     trail_seq;
+	unsigned		trail_fence_offs;
+	u64			trail_fence_gpu_addr;
+	volatile u32		*trail_fence_cpu_addr;
 	unsigned		cond_exe_offs;
 	u64			cond_exe_gpu_addr;
 	volatile u32		*cond_exe_cpu_addr;