diff options
| author | Tony Yi <Tony.Yi@amd.com> | 2025-02-26 17:03:10 -0500 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2025-03-05 10:47:03 -0500 |
| commit | a91d91b6004796b868374394962331a1322da7ab (patch) | |
| tree | b51752e912c72404a338f4ae3b60fa383a816538 /drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | |
| parent | ca17c8e149112270b598791bbd98968fe9231115 (diff) | |
drm/amdgpu: Add support for CPERs on virtualization
Add support for CPERs on VFs.
VFs do not receive PMFW messages directly; as such, they need to
query them from the host. To avoid hitting host event guard,
CPER queries need to be rate limited. CPER queries share the same
RAS telemetry buffer as error count query, so a mutex protecting
the shared buffer was added as well.
For readability, the amdgpu_detect_virtualization was refactored
into multiple individual functions.
Signed-off-by: Tony Yi <Tony.Yi@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 4dcb72d1bdda..5aadf24cb202 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -184,6 +184,9 @@ send_request: case IDH_REQ_RAS_ERROR_COUNT: event = IDH_RAS_ERROR_COUNT_READY; break; + case IDH_REQ_RAS_CPER_DUMP: + event = IDH_RAS_CPER_DUMP_READY; + break; default: break; } @@ -467,6 +470,16 @@ static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev) return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_ERROR_COUNT); } +static int xgpu_nv_req_ras_cper_dump(struct amdgpu_device *adev, u64 vf_rptr) +{ + uint32_t vf_rptr_hi, vf_rptr_lo; + + vf_rptr_hi = (uint32_t)(vf_rptr >> 32); + vf_rptr_lo = (uint32_t)(vf_rptr & 0xFFFFFFFF); + return xgpu_nv_send_access_requests_with_param( + adev, IDH_REQ_RAS_CPER_DUMP, vf_rptr_hi, vf_rptr_lo, 0); +} + const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .req_full_gpu = xgpu_nv_request_full_gpu_access, .rel_full_gpu = xgpu_nv_release_full_gpu_access, @@ -478,4 +491,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .ras_poison_handler = xgpu_nv_ras_poison_handler, .rcvd_ras_intr = xgpu_nv_rcvd_ras_intr, .req_ras_err_count = xgpu_nv_req_ras_err_count, + .req_ras_cper_dump = xgpu_nv_req_ras_cper_dump, }; |