[PATCH v2] drm/amdgpu/sdam: Skip SDMA queue reset for SRIOV
Lazar, Lijo
lijo.lazar at amd.com
Wed Mar 19 14:17:47 UTC 2025
On 3/18/2025 8:17 PM, Ahmad Rehman wrote:
> For SRIOV, skip the SDMA queue reset and return
> error. The engine/queue reset failure will trigger
> FLR in the sequence.
>
> v2: do not add queue reset support mask for sriov
>
> Signed-off-by: Ahmad Rehman <Ahmad.Rehman at amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar at amd.com>
Thanks,
Lijo
> ---
> drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> index fd34dc138081..e77c99180fa3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> @@ -1666,6 +1666,10 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
> {
> struct amdgpu_device *adev = ring->adev;
> u32 id = GET_INST(SDMA0, ring->me);
> +
> + if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
> + return -EOPNOTSUPP;
> +
> return amdgpu_sdma_reset_engine(adev, id, true);
> }
>
> @@ -2347,6 +2351,9 @@ static void sdma_v4_4_2_set_vm_pte_funcs(struct amdgpu_device *adev)
> */
> static void sdma_v4_4_2_update_reset_mask(struct amdgpu_device *adev)
> {
> + /* per queue reset not supported for SRIOV */
> + if (amdgpu_sriov_vf(adev))
> + return;
>
> /*
> * the user queue relies on MEC fw and pmfw when the sdma queue do reset.
More information about the amd-gfx
mailing list