diff options
| author | Vignesh Chander <Vignesh.Chander@amd.com> | 2024-06-24 16:44:26 -0500 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2024-06-27 17:31:37 -0400 |
| commit | cbda2758d8bfae323b846210a3e52f0ad5fe7164 (patch) | |
| tree | 034e4d34e668d0dd014fe139efa6e9736b7b28e4 /drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | |
| parent | 78146c1dcd220ae98fd5f4114f992299fc5ee161 (diff) | |
drm/amdgpu: process RAS fatal error MB notification
For RAS error scenario, VF guest driver will check mailbox
and set fed flag to avoid unnecessary HW accesses.
additionally, poll for reset completion message first
to avoid accidentally spamming multiple reset requests to host.
v2: add another mailbox check for handling case where kfd detects
timeout first
v3: set host_flr bit and use wait_for_reset
Signed-off-by: Vignesh Chander <Vignesh.Chander@amd.com>
Reviewed-by: Zhigang Luo <Zhigang.Luo@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 | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 17e1e8cc2437..f47bd7ada4d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -449,6 +449,13 @@ static void xgpu_nv_ras_poison_handler(struct amdgpu_device *adev, } } +static bool xgpu_nv_rcvd_ras_intr(struct amdgpu_device *adev) +{ + enum idh_event msg = xgpu_nv_mailbox_peek_msg(adev); + + return (msg == IDH_RAS_ERROR_DETECTED || msg == 0xFFFFFFFF); +} + 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, @@ -458,4 +465,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = { .wait_reset = xgpu_nv_wait_reset, .trans_msg = xgpu_nv_mailbox_trans_msg, .ras_poison_handler = xgpu_nv_ras_poison_handler, + .rcvd_ras_intr = xgpu_nv_rcvd_ras_intr, }; |