Re: [PATCH v4 12/12] drm/xe: Track parallel page fault activity in GT stats

[Maciej Patelczyk <maciej.patelczyk@intel.com>]

On 26/02/2026 05:28, Matthew Brost wrote:

> Add a new GT statistic, PARALLEL_PAGEFAULT_COUNT, to record when
> multiple page fault workers are active concurrently.
>
> When a worker dequeues a fault, scan peer workers for an active
> cache entry and increment the counter if another fault is already
> in flight. This provides basic visibility into parallel fault
> handling behavior for performance analysis and tuning.
>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_gt_stats.c       |  1 +
>   drivers/gpu/drm/xe/xe_gt_stats_types.h |  1 +
>   drivers/gpu/drm/xe/xe_pagefault.c      | 18 +++++++++++++++++-
>   3 files changed, 19 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c
> index cdd467dfb46d..621d1a2df067 100644
> --- a/drivers/gpu/drm/xe/xe_gt_stats.c
> +++ b/drivers/gpu/drm/xe/xe_gt_stats.c
> @@ -58,6 +58,7 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
>   	DEF_STAT_STR(CHAIN_IRQ_PAGEFAULT_COUNT, "chain_irq_pagefault_count"),
>   	DEF_STAT_STR(CHAIN_DRAIN_IRQ_PAGEFAULT_COUNT, "chain_drain_irq_pagefault_count"),
>   	DEF_STAT_STR(CHAIN_MISMATCH_PAGEFAULT_COUNT, "chain_mismatch_pagefault_count"),
> +	DEF_STAT_STR(PARALLEL_PAGEFAULT_COUNT, "parallel_pagefault_count"),
>   	DEF_STAT_STR(LAST_PAGEFAULT_COUNT, "last_pagefault_count"),
>   	DEF_STAT_STR(SVM_PAGEFAULT_COUNT, "svm_pagefault_count"),
>   	DEF_STAT_STR(TLB_INVAL, "tlb_inval_count"),
> diff --git a/drivers/gpu/drm/xe/xe_gt_stats_types.h b/drivers/gpu/drm/xe/xe_gt_stats_types.h
> index 591e614e1cfc..075a12152ae2 100644
> --- a/drivers/gpu/drm/xe/xe_gt_stats_types.h
> +++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h
> @@ -13,6 +13,7 @@ enum xe_gt_stats_id {
>   	XE_GT_STATS_ID_CHAIN_IRQ_PAGEFAULT_COUNT,
>   	XE_GT_STATS_ID_CHAIN_DRAIN_IRQ_PAGEFAULT_COUNT,
>   	XE_GT_STATS_ID_CHAIN_MISMATCH_PAGEFAULT_COUNT,
> +	XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT,
>   	XE_GT_STATS_ID_LAST_PAGEFAULT_COUNT,
>   	XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT,
>   	XE_GT_STATS_ID_TLB_INVAL,
> diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
> index d252a8c9d88c..2a37a4c97aad 100644
> --- a/drivers/gpu/drm/xe/xe_pagefault.c
> +++ b/drivers/gpu/drm/xe/xe_pagefault.c
> @@ -458,9 +458,10 @@ static bool xe_pagefault_queue_pop(struct xe_pagefault_queue *pf_queue,
>   {
>   	struct xe_device *xe = container_of(pf_queue, typeof(*xe),
>   					    usm.pf_queue);
> -	struct xe_pagefault_work *pf_work;
> +	struct xe_pagefault_work *pf_work, *__pf_work;
>   	struct xe_pagefault *lpf;
>   	size_t align = SZ_2M;
> +	int i;
>   
>   	guard(spinlock_irq)(&pf_queue->lock);
>   
> @@ -497,6 +498,21 @@ static bool xe_pagefault_queue_pop(struct xe_pagefault_queue *pf_queue,
>   	pf_work->cache.pf = lpf;
>   	lpf->consumer.alloc_state = XE_PAGEFAULT_ALLOC_STATE_ACTIVE;
>   
> +	for (i = 0, __pf_work = xe->usm.pf_workers;
> +	     i < xe->info.num_pf_work; ++i, ++__pf_work) {
> +		u64 cache_start = __pf_work->cache.start;
> +
> +		if (__pf_work == pf_work)
> +			continue;
> +
> +		if (cache_start != XE_PAGEFAULT_CACHE_START_INVALID) {
> +			xe_gt_stats_incr(xe_root_mmio_gt(xe),
> +					 XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT,
> +					 1);

In the xe_pagefault_queue_work() right after first ACTIVE pagefault is 
ACK'ed the worke's cache is invalidated.

Worker may still run releasing chained entries but this stat won't catch it.

Maybe it doesn't matter. Maybe the work is done (the 
xe_pagefault_service() being the core work) at that time.

Just noticing.

If it doesn't matter then

Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>

> +			break;
> +		}
> +	}
> +
>   	/* Drain queue until empty or new fault found */
>   	while (1) {
>   		if (pf_queue->tail == pf_queue->head)