[PATCH v9 12/12] drm/xe: Track parallel page fault activity in GT stats

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 <[email protected]>
Reviewed-by: Maciej Patelczyk <[email protected]>
---
 drivers/gpu/drm/xe/xe_gt_stats.c       |  1 +
 drivers/gpu/drm/xe/xe_gt_stats_types.h |  3 +++
 drivers/gpu/drm/xe/xe_pagefault.c      | 18 +++++++++++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c
index f2e77df0f224..2a40924660ee 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats.c
+++ b/drivers/gpu/drm/xe/xe_gt_stats.c
@@ -99,6 +99,7 @@ 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 ab5506f915cb..24abeb9f2137 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h
@@ -18,6 +18,8 @@
  *   that also drained the fault queue.
  * @XE_GT_STATS_ID_CHAIN_MISMATCH_PAGEFAULT_COUNT: Chained faults requeued
  *   because their fault range did not match the fault they were chained onto.
+ * @XE_GT_STATS_ID_PARALLEL_PAGEFAULT_COUNT: Faults dequeued while another page
+ *   fault worker was already handling a fault concurrently.
  * @XE_GT_STATS_ID_LAST_PAGEFAULT_COUNT: Faults whose range matched the last
  *   serviced range, allowing an immediate ack.
  *
@@ -144,6 +146,7 @@ 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 af19cd82e014..b2d7bca9e407 100644
--- a/drivers/gpu/drm/xe/xe_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_pagefault.c
@@ -460,9 +460,10 @@ 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);
 
@@ -499,6 +500,21 @@ 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);
+			break;
+		}
+	}
+
 	/* Drain queue until empty or new fault found */
 	while (1) {
 		if (xe_pagefault_queue_empty(pf_queue))
-- 
2.34.1