[PATCH] drm/amdgpu: fix deadlock of reservation between cs and gpu reset

[Chunming Zhou]

the case could happen when gpu reset:
1. when gpu reset, cs can be continue until sw queue is full, then push job will wait with holding pd reservation.
2. gpu_reset routine will also need pd reservation to restore page table from their shadow.
3. cs is waiting for gpu_reset complete, but gpu reset is waiting for cs releases reservation.

Change-Id: I0f66d04b2bef3433035109623c8a5c5992c84202
Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9edb1a4..8c6d036 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1076,7 +1076,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	amdgpu_job_free_resources(job);
 
 	trace_amdgpu_cs_ioctl(job);
-	amd_sched_entity_push_job(&job->base);
 
 	return 0;
 }
@@ -1132,6 +1131,8 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 out:
 	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
+	if (!r)
+		amd_sched_entity_push_job(&parser.job->base);
 	return r;
 }
 
-- 
1.9.1