On 2022-11-01 10:46, Graham Sider wrote:
Hang on MES timeout if halt_if_hws_hang is set to 1. Signed-off-by: Graham Sider <Graham.Sider@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
--- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++ drivers/gpu/drm/amd/amdgpu/mes_v10_1.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 4 ++++ 3 files changed, 10 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 0e6ddf05c23c..9999c18e7d8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -219,10 +219,12 @@ extern int amdgpu_use_xgmi_p2p; extern int sched_policy; extern bool debug_evictions; extern bool no_system_mem_limit; +extern int halt_if_hws_hang; #else static const int __maybe_unused sched_policy = KFD_SCHED_POLICY_HWS; static const bool __maybe_unused debug_evictions; /* = false */ static const bool __maybe_unused no_system_mem_limit; +static const int __maybe_unused halt_if_hws_hang; #endif #ifdef CONFIG_HSA_AMD_P2P extern bool pcie_p2p; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 1abdf8b7ab50..614394118a53 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -121,6 +121,10 @@ static int mes_v10_1_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, if (r < 1) { DRM_ERROR("MES failed to response msg=%d\n", x_pkt->header.opcode); + + while (halt_if_hws_hang) + schedule(); + return -ETIMEDOUT; }diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.cindex 27a330f51c7d..7bfe862aa83e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -129,6 +129,10 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, if (r < 1) { DRM_ERROR("MES failed to response msg=%d\n", x_pkt->header.opcode); + + while (halt_if_hws_hang) + schedule(); + return -ETIMEDOUT; }
