Re: [PATCH v3 12/36] drm/xe/vf: Add xe_gt_recovery_inprogress helper

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

On 9/29/2025 4:55 AM, Matthew Brost wrote:
> Add xe_gt_recovery_inprogress helper.
> 
> This helper serves as the singular point to determine whether a GT
> recovery is currently in progress. Expected callers include the GuC CT
> layer and the GuC submission layer. Atomically visable as soon as vCPU
> are unhalted until VF recovery completes.
> 
> v3:
>  - Add GT layer xe_gt_recovery_inprogress (Michal)
>  - Don't blow up in memirq not enabled (CI)
>  - Add __memirq_received with clear argument (Michal)
>  - xe_memirq_sw_int_0_irq_pending rename (Michal)
>  - Use offset in xe_memirq_sw_int_0_irq_pending (Michal)
> 
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt.h                | 13 ++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.c       | 25 ++++++++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_vf.h       |  2 +
>  drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h | 10 +++++
>  drivers/gpu/drm/xe/xe_memirq.c            | 48 +++++++++++++++++++++--
>  drivers/gpu/drm/xe/xe_memirq.h            |  2 +
>  6 files changed, 96 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
> index 41880979f4de..ee0239b2f48c 100644
> --- a/drivers/gpu/drm/xe/xe_gt.h
> +++ b/drivers/gpu/drm/xe/xe_gt.h
> @@ -12,6 +12,7 @@
>  
>  #include "xe_device.h"
>  #include "xe_device_types.h"
> +#include "xe_gt_sriov_vf.h"
>  #include "xe_hw_engine.h"
>  
>  #define for_each_hw_engine(hwe__, gt__, id__) \
> @@ -124,4 +125,16 @@ static inline bool xe_gt_is_usm_hwe(struct xe_gt *gt, struct xe_hw_engine *hwe)
>  		hwe->instance == gt->usm.reserved_bcs_instance;
>  }
>  
> +/**
> + * xe_gt_recovery_inprogress() - GT recovery in progress
> + * @gt: the &xe_gt
> + *
> + * Return: True if GT recovery in progress, False otherwise
> + */
> +static inline bool xe_gt_recovery_inprogress(struct xe_gt *gt)
> +{
> +	return IS_SRIOV_VF(gt_to_xe(gt)) &&
> +		xe_gt_sriov_vf_recovery_inprogress(gt);
> +}
> +
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
> index 016c867e5e2b..71309219a4b7 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_hxg_helpers.h"
>  #include "xe_guc_relay.h"
>  #include "xe_lrc.h"
> +#include "xe_memirq.h"
>  #include "xe_mmio.h"
>  #include "xe_sriov.h"
>  #include "xe_sriov_vf.h"
> @@ -828,6 +829,7 @@ void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt)
>  	struct xe_device *xe = gt_to_xe(gt);
>  
>  	xe_gt_assert(gt, IS_SRIOV_VF(xe));
> +	xe_gt_assert(gt, xe_gt_sriov_vf_recovery_inprogress(gt));

do we really need this?
with current code this function will be limited to memirq platforms only

>  
>  	set_bit(gt->info.id, &xe->sriov.vf.migration.gt_flags);
>  	/*
> @@ -1172,3 +1174,26 @@ void xe_gt_sriov_vf_print_version(struct xe_gt *gt, struct drm_printer *p)
>  	drm_printf(p, "\thandshake:\t%u.%u\n",
>  		   pf_version->major, pf_version->minor);
>  }
> +
> +/**
> + * xe_gt_sriov_vf_recovery_inprogress() - VF post migration recovery in progress
> + * @gt: the &xe_gt
> + *
> + * Return: True if VF post migration recovery in progress, False otherwise
> + */
> +bool xe_gt_sriov_vf_recovery_inprogress(struct xe_gt *gt)
> +{
> +	struct xe_memirq *memirq = &gt_to_tile(gt)->memirq;
> +
> +	xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
> +
> +	/*
> +	 * In practice, VF migration will never be supported on platforms
> +	 * without memirq, avoid CI blowing up on older VF platforms.
> +	 */

maybe instead of closing that door simply code this as:

	/* early detection until recovery starts */
	if (xe_device_uses_memirq(gt_to_xe(gt)) &&
	    xe_memirq_sw_int_0_irq_pending(memirq, &gt->uc.guc))
		return true;

	return READ_ONCE(gt->sriov.vf.migration.recovery_inprogress);

> +	if (!xe_device_uses_memirq(gt_to_xe(gt)))
> +	       return false;
> +
> +	return (xe_memirq_sw_int_0_irq_pending(memirq, &gt->uc.guc) ||
> +		READ_ONCE(gt->sriov.vf.migration.recovery_inprogress));
> +}
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> index 0af1dc769fe0..bb5f8eace19b 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
> @@ -25,6 +25,8 @@ 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);
>  
> +bool xe_gt_sriov_vf_recovery_inprogress(struct xe_gt *gt);
> +
>  u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt);
>  u16 xe_gt_sriov_vf_guc_ids(struct xe_gt *gt);
>  u64 xe_gt_sriov_vf_lmem(struct xe_gt *gt);
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> index d95857bd789b..7b10b8e1e10e 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf_types.h
> @@ -49,6 +49,14 @@ struct xe_gt_sriov_vf_runtime {
>  	} *regs;
>  };
>  
> +/**
> + * xe_gt_sriov_vf_migration - VF migration data.
> + */
> +struct xe_gt_sriov_vf_migration {
> +	/** @recovery_inprogress: VF post migration recovery in progress */
> +	bool recovery_inprogress;
> +};
> +
>  /**
>   * struct xe_gt_sriov_vf - GT level VF virtualization data.
>   */
> @@ -61,6 +69,8 @@ struct xe_gt_sriov_vf {
>  	struct xe_gt_sriov_vf_selfconfig self_config;
>  	/** @runtime: runtime data retrieved from the PF. */
>  	struct xe_gt_sriov_vf_runtime runtime;
> +	/** @migration: migration data for the VF. */
> +	struct xe_gt_sriov_vf_migration migration;
>  };
>  
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_memirq.c b/drivers/gpu/drm/xe/xe_memirq.c
> index 49c45ec3e83c..b681c67dcace 100644
> --- a/drivers/gpu/drm/xe/xe_memirq.c
> +++ b/drivers/gpu/drm/xe/xe_memirq.c
> @@ -398,8 +398,9 @@ void xe_memirq_postinstall(struct xe_memirq *memirq)
>  		memirq_set_enable(memirq, true);
>  }
>  
> -static bool memirq_received(struct xe_memirq *memirq, struct iosys_map *vector,
> -			    u16 offset, const char *name)
> +static bool __memirq_received(struct xe_memirq *memirq,
> +			      struct iosys_map *vector, u16 offset,
> +			      const char *name, bool clear)
>  {
>  	u8 value;
>  
> @@ -409,12 +410,26 @@ static bool memirq_received(struct xe_memirq *memirq, struct iosys_map *vector,
>  			memirq_err_ratelimited(memirq,
>  					       "Unexpected memirq value %#x from %s at %u\n",
>  					       value, name, offset);
> -		iosys_map_wr(vector, offset, u8, 0x00);
> +		if (clear)
> +			iosys_map_wr(vector, offset, u8, 0x00);
>  	}
>  
>  	return value;
>  }
>  
> +static bool memirq_received_noclear(struct xe_memirq *memirq,
> +				    struct iosys_map *vector,
> +				    u16 offset, const char *name)
> +{
> +	return __memirq_received(memirq, vector, offset, name, false);
> +}
> +
> +static bool memirq_received(struct xe_memirq *memirq, struct iosys_map *vector,
> +			    u16 offset, const char *name)
> +{
> +	return __memirq_received(memirq, vector, offset, name, true);
> +}
> +
>  static void memirq_dispatch_engine(struct xe_memirq *memirq, struct iosys_map *status,
>  				   struct xe_hw_engine *hwe)
>  {
> @@ -434,8 +449,16 @@ static void memirq_dispatch_guc(struct xe_memirq *memirq, struct iosys_map *stat
>  	if (memirq_received(memirq, status, ilog2(GUC_INTR_GUC2HOST), name))
>  		xe_guc_irq_handler(guc, GUC_INTR_GUC2HOST);
>  
> -	if (memirq_received(memirq, status, ilog2(GUC_INTR_SW_INT_0), name))
> +	/*
> +	 * We must wait to perform the clear operation until after
> +	 * xe_gt_sriov_vf_start_migration_recovery() runs, to avoid race
> +	 * conditions where xe_gt_sriov_vf_recovery_inprogress() returns false.
> +	 */
> +	if (memirq_received_noclear(memirq, status, ilog2(GUC_INTR_SW_INT_0),
> +				    name)) {
>  		xe_guc_irq_handler(guc, GUC_INTR_SW_INT_0);
> +		iosys_map_wr(status, ilog2(GUC_INTR_SW_INT_0), u8, 0x00);
> +	}
>  }
>  
>  /**
> @@ -460,6 +483,23 @@ void xe_memirq_hwe_handler(struct xe_memirq *memirq, struct xe_hw_engine *hwe)
>  	}
>  }
>  
> +/**
> + * xe_memirq_sw_int_0_irq_pending() - SW_INT_0 IRQ is pending
> + * @memirq: the &xe_memirq
> + * @guc: the &xe_guc to check for IRQ
> + *
> + * Return: True if SW_INT_0 IRQ is pending on @guc, False otherwise
> + */
> +bool xe_memirq_sw_int_0_irq_pending(struct xe_memirq *memirq,struct xe_guc *guc)
> +{
> +	struct xe_gt *gt = guc_to_gt(guc);
> +	u32 offset = xe_gt_is_media_type(gt) ? ilog2(INTR_MGUC) : ilog2(INTR_GUC);
> +	struct iosys_map map = IOSYS_MAP_INIT_OFFSET(&memirq->status, offset * SZ_16);
> +
> +	return memirq_received_noclear(memirq, &map, ilog2(GUC_INTR_SW_INT_0),
> +				       guc_name(guc));
> +}
> +
>  /**
>   * xe_memirq_handler - The `Memory Based Interrupts`_ Handler.
>   * @memirq: the &xe_memirq
> diff --git a/drivers/gpu/drm/xe/xe_memirq.h b/drivers/gpu/drm/xe/xe_memirq.h
> index 06130650e9d6..f87e1274b730 100644
> --- a/drivers/gpu/drm/xe/xe_memirq.h
> +++ b/drivers/gpu/drm/xe/xe_memirq.h
> @@ -25,4 +25,6 @@ void xe_memirq_handler(struct xe_memirq *memirq);
>  
>  int xe_memirq_init_guc(struct xe_memirq *memirq, struct xe_guc *guc);
>  
> +bool xe_memirq_sw_int_0_irq_pending(struct xe_memirq *memirq,struct xe_guc *guc);
> +
>  #endif