In multiple GPUs case, after a GPU has started resetting all GPUs on hive, other GPUs do not need to trigger GPU reset again.
Signed-off-by: YiPeng Chai <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index dbfc41ddc3c7..7d48541b03d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -4306,8 +4306,27 @@ int amdgpu_ras_reset_gpu(struct amdgpu_device *adev) ras->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE1_RESET; } - if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0) + if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0) { + struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev); + int hive_ras_recovery = 0; + + if (hive) { + hive_ras_recovery = atomic_read(&hive->ras_recovery); + amdgpu_put_xgmi_hive(hive); + } + /* In the case of multiple GPUs, after a GPU has started + * resetting all GPUs on hive, other GPUs do not need to + * trigger GPU reset again. + */ + if (!hive_ras_recovery) + amdgpu_reset_domain_schedule(ras->adev->reset_domain, &ras->recovery_work); + else + atomic_set(&ras->in_recovery, 0); + } else { + flush_work(&ras->recovery_work); amdgpu_reset_domain_schedule(ras->adev->reset_domain, &ras->recovery_work); + } + return 0; } -- 2.34.1
