Re: [PATCH v4 6/8] drm/xe/vf: Rebase MEMIRQ structures for all contexts after migration

[Michal Wajdeczko <michal.wajdeczko@intel.com>]

On 06.06.2025 02:18, Tomasz Lis wrote:
> All contexts require an update of state data, as the data includes
> GGTT references to memirq-related buffers.
> 
> Default contexts need these references updated as well, because they
> are not refreshed when a new context is created from them.
> 
> v2: Update addresses by xe_lrc_write_ctx_reg() rather than
>   set_memory_based_intr()
> v3: Renamed parameter, reordered parameters in some functs
> v4: Check if have MEMIRQ, move `xe_gt*` funct to proper file
> 
> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
> Cc: Michal Winiarski <michal.winiarski@intel.com>
> Acked-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_exec_queue.c  |  4 ++-
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 14 +++++++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.h |  1 +
>  drivers/gpu/drm/xe/xe_lrc.c         | 38 +++++++++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_lrc.h         |  2 ++
>  drivers/gpu/drm/xe/xe_sriov_vf.c    |  4 ++-
>  6 files changed, 61 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index c44a523ba906..86b2f9034902 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -1038,6 +1038,8 @@ void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q)
>  {
>  	int i;
>  
> -	for (i = 0; i < q->width; ++i)
> +	for (i = 0; i < q->width; ++i) {
> +		xe_lrc_update_memirq_regs_with_address(q->lrc[i], q->hwe);
>  		xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
> +	}
>  }
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 8fa210c0ef1a..0a5f78cf0490 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> @@ -26,6 +26,7 @@
>  #include "xe_guc_ct.h"
>  #include "xe_guc_hxg_helpers.h"
>  #include "xe_guc_relay.h"
> +#include "xe_lrc.h"
>  #include "xe_mmio.h"
>  #include "xe_sriov.h"
>  #include "xe_sriov_vf.h"
> @@ -709,6 +710,19 @@ int xe_gt_sriov_vf_connect(struct xe_gt *gt)
>  	return err;
>  }
>  
> +/**
> + * xe_gt_sriov_vf_default_lrcs_hwsp_rebase - Update GGTT references in HWSP of default LRCs.
> + * @gt: the &xe_gt struct instance
> + */
> +void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt)
> +{
> +	struct xe_hw_engine *hwe;
> +	enum xe_hw_engine_id id;
> +
> +	for_each_hw_engine(hwe, gt, id)
> +		xe_default_lrc_update_memirq_regs_with_address(hwe);
> +}

this function is not very specific to the data maintained by the VF

likely a better fit would be in xe_lrc.c or xe_hw_engine.c as

	xe_hw_engines_update_default_lrc(gt)
or
	xe_lrc_update_defaults(gt)


> +
>  /**
>   * xe_gt_sriov_vf_migrated_event_handler - Start a VF migration recovery,
>   *   or just mark that a GuC is ready for it.
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> index 6250fe774d89..5ab25a3c24ea 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> @@ -17,6 +17,7 @@ int xe_gt_sriov_vf_bootstrap(struct xe_gt *gt);
>  int xe_gt_sriov_vf_query_config(struct xe_gt *gt);
>  int xe_gt_sriov_vf_connect(struct xe_gt *gt);
>  int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt);
> +void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt);
>  int xe_gt_sriov_vf_notify_resfix_done(struct xe_gt *gt);
>  void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
>  
> diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
> index 72690f71289c..c74856f3974a 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.c
> +++ b/drivers/gpu/drm/xe/xe_lrc.c
> @@ -898,6 +898,44 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe)
>  	return data;
>  }
>  
> +/**
> + * xe_default_lrc_update_memirq_regs_with_address - Re-compute GGTT references in default LRC
> + * of given engine.
> + * @hwe: the &xe_hw_engine struct instance
> + */
> +void xe_default_lrc_update_memirq_regs_with_address(struct xe_hw_engine *hwe)
> +{
> +	struct xe_gt *gt = hwe->gt;
> +	u32 *regs;
> +
> +	if (!gt->default_lrc[hwe->class])
> +		return;
> +
> +	regs = gt->default_lrc[hwe->class] + LRC_PPHWSP_SIZE;
> +	set_memory_based_intr(regs, hwe);
> +}
> +
> +/**
> + * xe_lrc_update_memirq_regs_with_address - Re-compute GGTT references in mem interrupt data
> + * for given LRC.
> + * @lrc: the &xe_lrc struct instance
> + * @hwe: the &xe_hw_engine struct instance
> + */
> +void xe_lrc_update_memirq_regs_with_address(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
> +{
> +	struct xe_memirq *memirq = &gt_to_tile(hwe->gt)->memirq;
> +
> +	if (!xe_device_uses_memirq(gt_to_xe(hwe->gt)))
> +		return;
> +
> +	xe_lrc_write_ctx_reg(lrc, CTX_INT_MASK_ENABLE_PTR,
> +			     xe_memirq_enable_ptr(memirq));
> +	xe_lrc_write_ctx_reg(lrc, CTX_INT_STATUS_REPORT_PTR,
> +			     xe_memirq_status_ptr(memirq, hwe));
> +	xe_lrc_write_ctx_reg(lrc, CTX_INT_SRC_REPORT_PTR,
> +			     xe_memirq_source_ptr(memirq, hwe));
> +}
> +
>  static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
>  {
>  	u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt));
> diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
> index e7a99cfd0abe..801a6b943f6e 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.h
> +++ b/drivers/gpu/drm/xe/xe_lrc.h
> @@ -89,6 +89,8 @@ u32 xe_lrc_indirect_ring_ggtt_addr(struct xe_lrc *lrc);
>  u32 xe_lrc_ggtt_addr(struct xe_lrc *lrc);
>  u32 *xe_lrc_regs(struct xe_lrc *lrc);
>  void xe_lrc_update_hwctx_regs_with_address(struct xe_lrc *lrc);
> +void xe_default_lrc_update_memirq_regs_with_address(struct xe_hw_engine *hwe);
> +void xe_lrc_update_memirq_regs_with_address(struct xe_lrc *lrc, struct xe_hw_engine *hwe);
>  
>  u32 xe_lrc_read_ctx_reg(struct xe_lrc *lrc, int reg_nr);
>  void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val);
> diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
> index d54048bc4576..cf07d037a83a 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_vf.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
> @@ -247,8 +247,10 @@ static void vf_post_migration_fixup_contexts(struct xe_device *xe)
>  	struct xe_gt *gt;
>  	unsigned int id;
>  
> -	for_each_gt(gt, xe, id)
> +	for_each_gt(gt, xe, id) {
> +		xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
>  		xe_guc_contexts_hwsp_rebase(&gt->uc.guc);
> +	}
>  }
>  
>  static void vf_post_migration_fixup_ctb(struct xe_device *xe)