[PATCH v9 07/12] drm/xe: Track pagefault worker runtime

Add a GT stat measuring total time spent servicing pagefault workqueue
iterations. The counter accumulates the runtime of the pagefault worker
in microseconds, allowing correlation of fault storms and chaining
behavior with CPU time spent in the fault handler.

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      | 8 ++++++++
 3 files changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c
index 789397514f3e..513fe28c0e76 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats.c
+++ b/drivers/gpu/drm/xe/xe_gt_stats.c
@@ -101,6 +101,7 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
 	DEF_STAT_STR(SVM_TLB_INVAL_US, "svm_tlb_inval_us"),
 	DEF_STAT_STR(VMA_PAGEFAULT_COUNT, "vma_pagefault_count"),
 	DEF_STAT_STR(VMA_PAGEFAULT_KB, "vma_pagefault_kb"),
+	DEF_STAT_STR(PAGEFAULT_US, "pagefault_us"),
 	DEF_STAT_STR(INVALID_PREFETCH_PAGEFAULT_COUNT, "invalid_prefetch_pagefault_count"),
 	DEF_STAT_STR(SVM_4K_PAGEFAULT_COUNT, "svm_4K_pagefault_count"),
 	DEF_STAT_STR(SVM_64K_PAGEFAULT_COUNT, "svm_64K_pagefault_count"),
diff --git a/drivers/gpu/drm/xe/xe_gt_stats_types.h b/drivers/gpu/drm/xe/xe_gt_stats_types.h
index 425491bed6c4..a7021a298e3e 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h
@@ -22,6 +22,8 @@
  *   handled.
  * @XE_GT_STATS_ID_VMA_PAGEFAULT_KB: Size (KiB) of VMAs involved in
  *   buffer-object page fault handling.
+ * @XE_GT_STATS_ID_PAGEFAULT_US: Cumulative time (µs) handling of all page
+ *   faults.
  * @XE_GT_STATS_ID_INVALID_PREFETCH_PAGEFAULT_COUNT: GPU prefetch faults for
  *   addresses with no valid backing.
  *
@@ -133,6 +135,7 @@ enum xe_gt_stats_id {
 	XE_GT_STATS_ID_SVM_TLB_INVAL_US,
 	XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT,
 	XE_GT_STATS_ID_VMA_PAGEFAULT_KB,
+	XE_GT_STATS_ID_PAGEFAULT_US,
 	XE_GT_STATS_ID_INVALID_PREFETCH_PAGEFAULT_COUNT,
 	XE_GT_STATS_ID_SVM_4K_PAGEFAULT_COUNT,
 	XE_GT_STATS_ID_SVM_64K_PAGEFAULT_COUNT,
diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
index 2b0fabe29e25..65be8dd09e2f 100644
--- a/drivers/gpu/drm/xe/xe_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_pagefault.c
@@ -296,6 +296,8 @@ static void xe_pagefault_queue_work(struct work_struct *w)
 	struct xe_device *xe = pf_work->xe;
 	struct xe_pagefault_queue *pf_queue = &xe->usm.pf_queue;
 	struct xe_pagefault pf;
+	ktime_t start = xe_gt_stats_ktime_get();
+	struct xe_gt *gt = NULL;
 	unsigned long threshold;
 
 #define USM_QUEUE_MAX_RUNTIME_MS      20
@@ -307,6 +309,7 @@ static void xe_pagefault_queue_work(struct work_struct *w)
 		if (!pf.gt)	/* Fault squashed during reset */
 			continue;
 
+		gt = pf.gt;
 		err = xe_pagefault_service(&pf);
 		if (err) {
 			if (!(pf.consumer.access_type & XE_PAGEFAULT_ACCESS_PREFETCH)) {
@@ -329,6 +332,11 @@ static void xe_pagefault_queue_work(struct work_struct *w)
 		}
 	}
 #undef USM_QUEUE_MAX_RUNTIME_MS
+
+	if (gt)
+		xe_gt_stats_incr(xe_root_mmio_gt(gt_to_xe(gt)),
+				 XE_GT_STATS_ID_PAGEFAULT_US,
+				 xe_gt_stats_ktime_us_delta(start));
 }
 
 static int xe_pagefault_queue_init(struct xe_device *xe,
-- 
2.34.1