[PATCH v2 21/33] drm/xe: Add defrag GT stats

From: Matthew Brost

Date: Fri Jul 10 2026 - 17:56:21 EST


Add observability for the page defragmentation worker.

Introduce four primary-GT statistics counters: defrag_added_count
(BOs queued onto the defrag list after being backed at a sub-optimal
page order), defrag_success_count (BOs fully re-backed at the beneficial
order), defrag_partial_success_count (BOs only partially re-backed at the
beneficial order) defrag_failed_count (attempts that failed and left the
BO on its original backing) and defrag_mb_moved. The
ineligible/already-removed fast path is intentionally not counted as
either success or failure.

Cc: Carlos Santa <carlos.santa@xxxxxxxxx>
Cc: Ryan Neph <ryanneph@xxxxxxxxxx>
Cc: Christian Koenig <christian.koenig@xxxxxxx>
Cc: Huang Rui <ray.huang@xxxxxxx>
Cc: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Maarten Lankhorst <maarten.lankhorst@xxxxxxxxxxxxxxx>
Cc: Maxime Ripard <mripard@xxxxxxxxxx>
Cc: Thomas Zimmermann <tzimmermann@xxxxxxx>
Cc: David Airlie <airlied@xxxxxxxxx>
Cc: Simona Vetter <simona@xxxxxxxx>
Cc: dri-devel@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Assisted-by: GitHub_Copilot:claude-opus-4.8
Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
---
drivers/gpu/drm/xe/xe_bo.c | 17 +++++++++++++++++
drivers/gpu/drm/xe/xe_gt_stats.c | 5 +++++
drivers/gpu/drm/xe/xe_gt_stats_types.h | 17 +++++++++++++++++
3 files changed, 39 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 6a847e42946c..c1bbcf0d21ed 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -26,6 +26,7 @@
#include "xe_dma_buf.h"
#include "xe_drm_client.h"
#include "xe_ggtt.h"
+#include "xe_gt_stats.h"
#include "xe_map.h"
#include "xe_migrate.h"
#include "xe_pat.h"
@@ -1154,6 +1155,8 @@ static void xe_bo_defrag_add(struct xe_bo *bo)
xe->mem.defrag.interval_ms = XE_BO_DEFRAG_INTERVAL_MS;
list_add_tail(&bo->defrag_link, &xe->mem.defrag.list);
atomic_inc(&xe->mem.defrag.count);
+ xe_gt_stats_incr(xe_root_mmio_gt(xe),
+ XE_GT_STATS_ID_DEFRAG_ADDED_COUNT, 1);
}
}

@@ -1264,6 +1267,20 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo,
xe_dbg(xe, "Defrag attempt on BO size=%zu: ret=%pe consumed=%llu\n",
xe_bo_size(bo), ERR_PTR(ret), *consumed);

+ if (!ret && ttm_tt_is_beneficial_order_failed(bo->ttm.ttm))
+ xe_gt_stats_incr(xe_root_mmio_gt(xe),
+ XE_GT_STATS_ID_DEFRAG_PARTIAL_SUCCESS_COUNT,
+ 1);
+ else
+ xe_gt_stats_incr(xe_root_mmio_gt(xe),
+ ret ? XE_GT_STATS_ID_DEFRAG_FAILED_COUNT :
+ XE_GT_STATS_ID_DEFRAG_SUCCESS_COUNT, 1);
+
+ if (!ret)
+ xe_gt_stats_incr(xe_root_mmio_gt(xe),
+ XE_GT_STATS_ID_DEFRAG_MB_MOVED,
+ *consumed >> 20);
+
unlock:
xe_bo_unlock(bo);
return ret;
diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c
index 789397514f3e..68e60d9500c8 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats.c
+++ b/drivers/gpu/drm/xe/xe_gt_stats.c
@@ -154,6 +154,11 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
DEF_STAT_STR(PRL_2M_ENTRY_COUNT, "prl_2m_entry_count"),
DEF_STAT_STR(PRL_ISSUED_COUNT, "prl_issued_count"),
DEF_STAT_STR(PRL_ABORTED_COUNT, "prl_aborted_count"),
+ DEF_STAT_STR(DEFRAG_ADDED_COUNT, "defrag_added_count"),
+ DEF_STAT_STR(DEFRAG_SUCCESS_COUNT, "defrag_success_count"),
+ DEF_STAT_STR(DEFRAG_PARTIAL_SUCCESS_COUNT, "defrag_partial_success_count"),
+ DEF_STAT_STR(DEFRAG_FAILED_COUNT, "defrag_failed_count"),
+ DEF_STAT_STR(DEFRAG_MB_MOVED, "defrag_mb_moved"),
};

/**
diff --git a/drivers/gpu/drm/xe/xe_gt_stats_types.h b/drivers/gpu/drm/xe/xe_gt_stats_types.h
index 425491bed6c4..c42b494390f8 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_stats_types.h
@@ -122,6 +122,18 @@
* @XE_GT_STATS_ID_PRL_ABORTED_COUNT: Times the page reclaim process was
* aborted.
*
+ * @XE_GT_STATS_ID_DEFRAG_ADDED_COUNT: Times a buffer object was added to the
+ * page defragmentation list after being backed at a sub-optimal page order.
+ * @XE_GT_STATS_ID_DEFRAG_SUCCESS_COUNT: Times the defrag worker successfully
+ * re-backed a buffer object at the beneficial page order.
+ * @XE_GT_STATS_ID_DEFRAG_PARTIAL_SUCCESS_COUNT: Times the defrag worker
+ * partially re-backed a buffer object at the beneficial page order.
+ * @XE_GT_STATS_ID_DEFRAG_FAILED_COUNT: Times the defrag worker failed to
+ * re-back a buffer object at the beneficial page order.
+ * @XE_GT_STATS_ID_DEFRAG_MB_MOVED: Data (MiB) actually (re)allocated while
+ * re-backing buffer objects at the beneficial page order. Chunks borrowed
+ * from the old backing for free are not counted.
+ *
* @__XE_GT_STATS_NUM_IDS: Number of valid IDs; not a real counter.
*
* See Documentation/gpu/xe/xe_gt_stats.rst.
@@ -181,6 +193,11 @@ enum xe_gt_stats_id {
XE_GT_STATS_ID_PRL_2M_ENTRY_COUNT,
XE_GT_STATS_ID_PRL_ISSUED_COUNT,
XE_GT_STATS_ID_PRL_ABORTED_COUNT,
+ XE_GT_STATS_ID_DEFRAG_ADDED_COUNT,
+ XE_GT_STATS_ID_DEFRAG_SUCCESS_COUNT,
+ XE_GT_STATS_ID_DEFRAG_PARTIAL_SUCCESS_COUNT,
+ XE_GT_STATS_ID_DEFRAG_FAILED_COUNT,
+ XE_GT_STATS_ID_DEFRAG_MB_MOVED,
/* must be the last entry */
__XE_GT_STATS_NUM_IDS,
};
--
2.34.1