leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

drm/amdgpu: fix deadlock of reservation between cs and gpu reset v2

Browse Source 
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.

v2: handle amdgpu_cs_submit error path.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Chunming Zhou 2017-04-27 15:13:52 +08:00 committed by Alex Deucher
parent 44eb8c1b33
commit 10e709cb29
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
View File

@ -1074,6 +1074,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence); cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence);
job->uf_sequence = cs->out.handle; job->uf_sequence = cs->out.handle;
amdgpu_job_free_resources(job); amdgpu_job_free_resources(job);
amdgpu_cs_parser_fini(p, 0, true);
trace_amdgpu_cs_ioctl(job); trace_amdgpu_cs_ioctl(job);
amd_sched_entity_push_job(&job->base); amd_sched_entity_push_job(&job->base);
@ -1129,7 +1130,10 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
goto out; goto out;
r = amdgpu_cs_submit(&parser, cs); r = amdgpu_cs_submit(&parser, cs);
if (r)
goto out;
return 0;
out: out:
amdgpu_cs_parser_fini(&parser, r, reserved_buffers); amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
return r; return r;