[PATCH v11 1/1] drm/xe: Add helper macro to loop each DSS

[Michal Wajdeczko]

On 14.03.2024 17:00, Zhanjun Dong wrote:
> Add helper macro to loop each DSS. This is a precursor patch to allow
> for easier iteration through MCR registers and other per-DSS uses.
> 
> Signed-off-by: Zhanjun Dong <zhanjun.dong at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_mcr.c      | 34 ++++++++++++++++++++++++-----
>  drivers/gpu/drm/xe/xe_gt_mcr.h      | 25 +++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_gt_topology.c |  3 ---
>  drivers/gpu/drm/xe/xe_gt_types.h    |  6 +++--
>  4 files changed, 57 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
> index a7ab9ba645f9..866bbd26ba3f 100644
> --- a/drivers/gpu/drm/xe/xe_gt_mcr.c
> +++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
> @@ -6,6 +6,7 @@
>  #include "xe_gt_mcr.h"
>  
>  #include "regs/xe_gt_regs.h"
> +#include "xe_assert.h"
>  #include "xe_gt.h"
>  #include "xe_gt_topology.h"
>  #include "xe_gt_types.h"
> @@ -294,14 +295,35 @@ static void init_steering_mslice(struct xe_gt *gt)
>  	gt->steering[LNCF].instance_target = 0;		/* unused */
>  }
>  
> -static void init_steering_dss(struct xe_gt *gt)
> +static unsigned int dss_per_group(struct xe_gt *gt)
> +{
> +	return gt_to_xe(gt)->info.platform == XE_PVC ? 8 : 4;
> +}
> +
> +/**
> + * xe_gt_mcr_get_dss_steering - Get the group/instance steering for a DSS
> + * @gt: GT structure
> + * @dss: DSS ID to obtain steering for
> + * @group: pointer to storage for steering group ID
> + * @instance: pointer to storage for steering instance ID
> + */
> +void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance)
>  {
> -	unsigned int dss = min(xe_dss_mask_group_ffs(gt->fuse_topo.g_dss_mask, 0, 0),
> -			       xe_dss_mask_group_ffs(gt->fuse_topo.c_dss_mask, 0, 0));
> -	unsigned int dss_per_grp = gt_to_xe(gt)->info.platform == XE_PVC ? 8 : 4;
> +	int dss_per_grp = dss_per_group(gt);
> +
> +	xe_gt_assert(gt, dss < XE_MAX_DSS_FUSE_BITS);
> +
> +	*group = dss / dss_per_grp;
> +	*instance = dss % dss_per_grp;
> +}
>  
> -	gt->steering[DSS].group_target = dss / dss_per_grp;
> -	gt->steering[DSS].instance_target = dss % dss_per_grp;
> +static void init_steering_dss(struct xe_gt *gt)
> +{
> +	xe_gt_mcr_get_dss_steering(gt,
> +				   min(xe_dss_mask_group_ffs(gt->fuse_topo.g_dss_mask, 0, 0),
> +				       xe_dss_mask_group_ffs(gt->fuse_topo.c_dss_mask, 0, 0)),
> +				   &gt->steering[DSS].group_target,
> +				   &gt->steering[DSS].instance_target);
>  }
>  
>  static void init_steering_oaddrm(struct xe_gt *gt)
> diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.h b/drivers/gpu/drm/xe/xe_gt_mcr.h
> index 27ca1bc880a0..77fd858b2c0d 100644
> --- a/drivers/gpu/drm/xe/xe_gt_mcr.h
> +++ b/drivers/gpu/drm/xe/xe_gt_mcr.h
> @@ -7,6 +7,7 @@
>  #define _XE_GT_MCR_H_
>  
>  #include "regs/xe_reg_defs.h"
> +#include "xe_gt_topology.h"

if you really don't want to define for_each_dss() in "xe_gt_topology.h"
then likely you just need to include "xe_gt_types.h"

>  
>  struct drm_printer;
>  struct xe_gt;
> @@ -25,5 +26,29 @@ void xe_gt_mcr_multicast_write(struct xe_gt *gt, struct xe_reg_mcr mcr_reg,
>  			       u32 value);
>  
>  void xe_gt_mcr_steering_dump(struct xe_gt *gt, struct drm_printer *p);
> +void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance);
> +
> +/*
> + * Loop over each DSS with the bit is 1 in geometry or compute mask
> + * @dss: DSS ID to obtain steering for

hmm, macro looks like more generic than its first usage, so maybe:

	@dss: iterated DSS bit from the DSS mask

> + * @gt: GT structure
> + */
> +#define for_each_dss(dss, gt) \
> +	for_each_or_bit((dss), \
> +			(gt)->fuse_topo.g_dss_mask, \
> +			(gt)->fuse_topo.c_dss_mask, \
> +			XE_MAX_DSS_FUSE_BITS)

and IMO this macro will look better in xe_gt_topology.h

but otherwise LGTM, so with macro moved or with fixed include, this is:

Reviewed-by: Michal Wajdeczko <michal.wajdeczko at intel.com>

> +
> +/*
> + * Loop over each DSS and determine the group and instance IDs that
> + * should be used to steer MCR accesses toward this DSS.
> + * @dss: DSS ID to obtain steering for
> + * @gt: GT structure
> + * @group: steering group ID, data type: u16
> + * @instance: steering instance ID, data type: u16
> + */
> +#define for_each_dss_steering(dss, gt, group, instance) \
> +	for_each_dss((dss), (gt)) \
> +		for_each_if((xe_gt_mcr_get_dss_steering((gt), (dss), &(group), &(instance)), true))
>  
>  #endif /* _XE_GT_MCR_H_ */
> diff --git a/drivers/gpu/drm/xe/xe_gt_topology.c b/drivers/gpu/drm/xe/xe_gt_topology.c
> index 5dc62fe1be49..f5773a14f3c8 100644
> --- a/drivers/gpu/drm/xe/xe_gt_topology.c
> +++ b/drivers/gpu/drm/xe/xe_gt_topology.c
> @@ -11,9 +11,6 @@
>  #include "xe_gt.h"
>  #include "xe_mmio.h"
>  
> -#define XE_MAX_DSS_FUSE_BITS (32 * XE_MAX_DSS_FUSE_REGS)
> -#define XE_MAX_EU_FUSE_BITS (32 * XE_MAX_EU_FUSE_REGS)
> -
>  static void
>  load_dss_mask(struct xe_gt *gt, xe_dss_mask_t mask, int numregs, ...)
>  {
> diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
> index 70c615dd1498..f6da2ad9719f 100644
> --- a/drivers/gpu/drm/xe/xe_gt_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_types.h
> @@ -25,10 +25,12 @@ enum xe_gt_type {
>  };
>  
>  #define XE_MAX_DSS_FUSE_REGS	3
> +#define XE_MAX_DSS_FUSE_BITS	(32 * XE_MAX_DSS_FUSE_REGS)
>  #define XE_MAX_EU_FUSE_REGS	1
> +#define XE_MAX_EU_FUSE_BITS	(32 * XE_MAX_EU_FUSE_REGS)
>  
> -typedef unsigned long xe_dss_mask_t[BITS_TO_LONGS(32 * XE_MAX_DSS_FUSE_REGS)];
> -typedef unsigned long xe_eu_mask_t[BITS_TO_LONGS(32 * XE_MAX_EU_FUSE_REGS)];
> +typedef unsigned long xe_dss_mask_t[BITS_TO_LONGS(XE_MAX_DSS_FUSE_BITS)];
> +typedef unsigned long xe_eu_mask_t[BITS_TO_LONGS(XE_MAX_EU_FUSE_BITS)];
>  
>  struct xe_mmio_range {
>  	u32 start;