Re: [PATCH 04/12] drm/amdgpu: add amdgpu_xcp_get_xcc_mask helper

["Lazar, Lijo" <lijo.lazar@amd.com>]

On 22-Sep-26 1:33 AM, James Zhu wrote:
> Add amdgpu_xcp_get_xcc_mask() to return the XCC instance mask for a given
> XCP partition. This is needed by upcoming SPM (Stream Performance Monitor)
> support, which programs hardware per partition and must operate only on
> the XCCs that belong to a given XCP.
> 
> For partitioned systems the helper returns only the XCCs belonging to the
> specified XCP. When @xcp_id is AMDGPU_XCP_NO_PARTITION (or the device is
> not partitioned) it returns the device's full XCC mask (e.g. 0xFF for an
> 8-XCC device). Note that the full device mask is returned even on a
> partitioned device; callers that require partition isolation (e.g. SPM)
> must reject AMDGPU_XCP_NO_PARTITION on a partitioned device themselves.
> 

Could you clarifiy on this part - xcp_id = AMDGPU_XCP_NO_PARTITION usage 
on 8-XCC device?

The default state on a multi-XCC device after driver load is all XCCs in 
a single partition called SPX. It should have at least one partition valid.

Thanks,
Lioj

> amdgpu_xcp_get_num_xcc() is reworked to take (adev, xcp_id) and derive the
> count from this helper via hweight32(). The helper is defined out of line
> in amdgpu_xcp.c so that the static inline in amdgpu_xcp.h never has to
> dereference the (incomplete) struct amdgpu_device; it only passes the
> pointer through.
> 
> This is a user-visible change: amdgpu_xcp_get_num_xcc() previously
> returned 1 for non-partitioned systems (and for AMDGPU_XCP_NO_PARTITION),
> and now returns the actual XCC count (e.g. 8 for an 8-XCC device). CWSR
> callers (amdgpu_kms.c, amdgpu_userq.c, mes_userqueue.c) scale the per-XCC
> control-stack and debug-memory sizes by num_xcc, so the uAPI-visible
> ctl_stack_size and dbg_mem_size values grow accordingly to match the
> actual hardware resource requirements, which were previously undersized.
> 
> Fixes: 4cd417bfec49 ("drm/amdgpu: Add helper function to get xcc count")
> Signed-off-by: James Zhu <James.Zhu@amd.com>
> Reviewed-by: Bing Ma <bing.ma@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    |  2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c  |  2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c    | 48 ++++++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h    | 32 +++++++--------
>   drivers/gpu/drm/amd/amdgpu/mes_userqueue.c |  3 +-
>   5 files changed, 66 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 57fa69c0382d..7782ccd4d28f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -1501,7 +1501,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
>   		fpriv = (struct amdgpu_fpriv *)filp->driver_priv;
>   		if (!amdgpu_trap_is_enabled(adev) || !fpriv->trap_obj)
>   			return -EOPNOTSUPP;
> -		num_xcc = amdgpu_xcp_get_num_xcc(adev->xcp_mgr, fpriv->xcp_id);
> +		num_xcc = amdgpu_xcp_get_num_xcc(adev, fpriv->xcp_id);
>   		cwsr_info.ctl_stack_size =
>   			adev->trap_info->cwsr.xcc_ctl_stack_sz * num_xcc;
>   		cwsr_info.dbg_mem_size =
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> index db09e879b85e..d19af9cb6ee1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> @@ -258,7 +258,7 @@ int amdgpu_userq_input_trap_params_validate(struct amdgpu_usermode_queue *queue,
>   	int num_xcc;
>   	int r;
>   
> -	num_xcc = amdgpu_xcp_get_num_xcc(adev->xcp_mgr, fpriv->xcp_id);
> +	num_xcc = amdgpu_xcp_get_num_xcc(adev, fpriv->xcp_id);
>   	r = amdgpu_trap_validate_params(queue->userq_mgr->adev, trap_params,
>   					num_xcc);
>   	if (r)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> index 2a56f5ec9c76..90846d55292b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> @@ -390,6 +390,54 @@ int amdgpu_xcp_get_inst_details(struct amdgpu_xcp *xcp,
>   	return 0;
>   }
>   
> +/**
> + * amdgpu_xcp_get_xcc_mask - Get XCC instance mask for a partition
> + * @adev: amdgpu device pointer
> + * @xcp_id: XCP partition ID
> + * @xcc_mask: output parameter for XCC instance mask
> + *
> + * Returns the XCC instance mask for the specified XCP partition.
> + * For partitioned systems, returns only the XCCs belonging to this XCP.
> + *
> + * When @xcp_id is AMDGPU_XCP_NO_PARTITION (or the device is not
> + * partitioned), the device's full XCC mask is returned (e.g. 0xFF for an
> + * 8-XCC device). Note that the full device mask is returned even on a
> + * partitioned device: callers that require partition isolation (e.g. SPM)
> + * must reject AMDGPU_XCP_NO_PARTITION on a partitioned device themselves.
> + *
> + * Note: On error, xcc_mask is undefined. Callers must check return code
> + * and only read xcc_mask when return == 0.
> + *
> + * Return: 0 on success (non-partitioned systems or valid XCP found),
> + *         -EINVAL if xcc_mask is NULL, no matching XCP id is found, or the
> + *         partition's GFX IP details are unavailable
> + */
> +int amdgpu_xcp_get_xcc_mask(struct amdgpu_device *adev, int xcp_id,
> +			    uint32_t *xcc_mask)
> +{
> +	struct amdgpu_xcp_mgr *xcp_mgr = adev->xcp_mgr;
> +	struct amdgpu_xcp *xcp;
> +	int i;
> +
> +	if (!xcc_mask)
> +		return -EINVAL;
> +
> +	if (!xcp_mgr || xcp_id == AMDGPU_XCP_NO_PARTITION) {
> +		/* Non-partitioned: return the device's full XCC mask. */
> +		*xcc_mask = adev->gfx.xcc_mask;
> +		return 0;
> +	}
> +
> +	/* Partitioned system: get this XCP's XCCs */
> +	for_each_xcp(xcp_mgr, xcp, i) {
> +		if (xcp->id == xcp_id)
> +			return amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX,
> +							   xcc_mask);
> +	}
> +
> +	return -EINVAL;
> +}
> +
>   int amdgpu_xcp_dev_register(struct amdgpu_device *adev,
>   			const struct pci_device_id *ent)
>   {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
> index 692508be23fb..6eed82ad49b1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
> @@ -44,6 +44,7 @@
>   #define XCP_INST_MASK(num_inst, xcp_id)		\
>   	(num_inst ? GENMASK(num_inst - 1, 0) << (xcp_id * num_inst) : 0)
>   
> +struct amdgpu_device;
>   struct amdgpu_fpriv;
>   
>   enum AMDGPU_XCP_IP_BLOCK {
> @@ -219,26 +220,23 @@ amdgpu_get_next_xcp(struct amdgpu_xcp_mgr *xcp_mgr, int *from)
>   	for (i = 0, xcp = amdgpu_get_next_xcp(xcp_mgr, &i); xcp; \
>   	     ++i, xcp = amdgpu_get_next_xcp(xcp_mgr, &i))
>   
> -static inline int amdgpu_xcp_get_num_xcc(struct amdgpu_xcp_mgr *xcp_mgr,
> -					 int xcp_id)
> +int amdgpu_xcp_get_xcc_mask(struct amdgpu_device *adev, int xcp_id,
> +			    uint32_t *xcc_mask);
> +
> +static inline int amdgpu_xcp_get_num_xcc(struct amdgpu_device *adev, int xcp_id)
>   {
> -	struct amdgpu_xcp *xcp;
>   	uint32_t xcc_mask;
> -	int i, r;
> -
> -	if (!xcp_mgr || xcp_id == AMDGPU_XCP_NO_PARTITION)
> +	int r, count;
> +
> +	/* Derive the XCC count from the partition's XCC mask (or the full
> +	 * device mask when not partitioned). amdgpu_xcp_get_xcc_mask()
> +	 * handles both partitioned and non-partitioned cases.
> +	 */
> +	r = amdgpu_xcp_get_xcc_mask(adev, xcp_id, &xcc_mask);
> +	if (unlikely(r))
>   		return 1;
> -	for_each_xcp(xcp_mgr, xcp, i) {
> -		if (xcp->id == xcp_id) {
> -			r = amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX,
> -							&xcc_mask);
> -			if (unlikely(r))
> -				return 1;
> -			else
> -				return hweight32(xcc_mask);
> -		}
> -	}
>   
> -	return 1;
> +	count = hweight32(xcc_mask);
> +	return count ? count : 1;
>   }
>   #endif
> diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
> index 16aa22b25098..1c7b2f3227e5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
> @@ -503,8 +503,7 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
>   				uq_mgr_to_fpriv(queue->userq_mgr);
>   			int num_xcc;
>   
> -			num_xcc = amdgpu_xcp_get_num_xcc(adev->xcp_mgr,
> -							 fpriv->xcp_id);
> +			num_xcc = amdgpu_xcp_get_num_xcc(adev, fpriv->xcp_id);
>   			trap_params.ctx_save_area_address =
>   				compute_mqd->ctx_save_area_va;
>   			trap_params.cwsr_sz = compute_mqd->ctx_save_area_size;