[PATCH v3] drm/amdgpu: fix incorrect VCN revision in SRIOV

Lazar, Lijo lijo.lazar at amd.com
Thu Dec 9 08:53:19 UTC 2021



On 12/9/2021 1:56 PM, Leslie Shi wrote:
> Guest OS will setup VCN instance 1 which is disabled as an enabled instance and
> execute initialization work on it, but this causes VCN ib ring test failure
> on the disabled VCN instance during modprobe:
> 
> amdgpu 0000:00:08.0: amdgpu: ring vcn_enc_1.0 uses VM inv eng 5 on hub 1
> amdgpu 0000:00:08.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on vcn_dec_0 (-110).
> amdgpu 0000:00:08.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on vcn_enc_0.0 (-110).
> [drm:amdgpu_device_delayed_init_work_handler [amdgpu]] *ERROR* ib ring test failed (-110).
> 
> v2: drop amdgpu_discovery_get_vcn_version and rename sriov_config to
> vcn_config
> v3: modify VCN's revision in SR-IOV and bare-metal
> 
> Fixes: 36b7d5646476 ("drm/amdgpu: handle SRIOV VCN revision parsing")
> Signed-off-by: Leslie Shi <Yuliang.Shi at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 29 ++++++-------------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h |  2 --
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c       | 15 +++-------
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h       |  2 +-
>   4 files changed, 14 insertions(+), 34 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> index 552031950518..f31bc0187394 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
> @@ -380,18 +380,15 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
>   				  ip->revision);
>   
>   			if (le16_to_cpu(ip->hw_id) == VCN_HWID) {
> -				if (amdgpu_sriov_vf(adev)) {
> -					/* SR-IOV modifies each VCN’s revision (uint8)
> -					 * Bit [5:0]: original revision value
> -					 * Bit [7:6]: en/decode capability:
> -					 *     0b00 : VCN function normally
> -					 *     0b10 : encode is disabled
> -					 *     0b01 : decode is disabled
> -					 */
> -					adev->vcn.sriov_config[adev->vcn.num_vcn_inst] =
> -						(ip->revision & 0xc0) >> 6;
> -					ip->revision &= ~0xc0;
> -				}
> +				/* Bit [5:0]: original revision value
> +				 * Bit [7:6]: en/decode capability:
> +				 *     0b00 : VCN function normally
> +				 *     0b10 : encode is disabled
> +				 *     0b01 : decode is disabled
> +				 */
> +				adev->vcn.vcn_config[adev->vcn.num_vcn_inst] =
> +					ip->revision & 0xc0;
> +				ip->revision &= ~0xc0;
>   				adev->vcn.num_vcn_inst++;
>   			}
>   			if (le16_to_cpu(ip->hw_id) == SDMA0_HWID ||
> @@ -485,14 +482,6 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int n
>   	return -EINVAL;
>   }
>   
> -
> -int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
> -				     int *major, int *minor, int *revision)
> -{
> -	return amdgpu_discovery_get_ip_version(adev, VCN_HWID,
> -					       vcn_instance, major, minor, revision);
> -}
> -
>   void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
>   {
>   	struct binary_header *bhdr;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
> index 0ea029e3b850..14537cec19db 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
> @@ -33,8 +33,6 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev);
>   int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int number_instance,
>                                       int *major, int *minor, int *revision);
>   
> -int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
> -				     int *major, int *minor, int *revision);
>   int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev);
>   int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> index 2658414c503d..38036cbf6203 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
> @@ -284,20 +284,13 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
>   bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
>   {
>   	bool ret = false;
> +	int vcn_config = adev->vcn.vcn_config[vcn_instance];

Missed it. I guess there should also be a check for valid instance, 
otherwise it could return false (by default nothing is disabled for a 
non-existent VCN instance).

If the check is not there in the caller and assuming instance is 0 based 
index,
	vcn_instance >= adev->vcn.num_vcn_inst
		return true;

Thanks,
Lijo

>   
> -	int major;
> -	int minor;
> -	int revision;
> -
> -	/* if cannot find IP data, then this VCN does not exist */
> -	if (amdgpu_discovery_get_vcn_version(adev, vcn_instance, &major, &minor, &revision) != 0)
> -		return true;
> -
> -	if ((type == VCN_ENCODE_RING) && (revision & VCN_BLOCK_ENCODE_DISABLE_MASK)) {
> +	if ((type == VCN_ENCODE_RING) && (vcn_config & VCN_BLOCK_ENCODE_DISABLE_MASK)) {
>   		ret = true;
> -	} else if ((type == VCN_DECODE_RING) && (revision & VCN_BLOCK_DECODE_DISABLE_MASK)) {
> +	} else if ((type == VCN_DECODE_RING) && (vcn_config & VCN_BLOCK_DECODE_DISABLE_MASK)) {
>   		ret = true;
> -	} else if ((type == VCN_UNIFIED_RING) && (revision & VCN_BLOCK_QUEUE_DISABLE_MASK)) {
> +	} else if ((type == VCN_UNIFIED_RING) && (vcn_config & VCN_BLOCK_QUEUE_DISABLE_MASK)) {
>   		ret = true;
>   	}
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> index 938a5ead3f20..5d3728b027d3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
> @@ -235,7 +235,7 @@ struct amdgpu_vcn {
>   
>   	uint8_t	num_vcn_inst;
>   	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
> -	uint8_t			 sriov_config[AMDGPU_MAX_VCN_INSTANCES];
> +	uint8_t			 vcn_config[AMDGPU_MAX_VCN_INSTANCES];
>   	struct amdgpu_vcn_reg	 internal;
>   	struct mutex		 vcn_pg_lock;
>   	struct mutex		vcn1_jpeg1_workaround;
> 


More information about the amd-gfx mailing list