[PATCH v2 24/33] drm/xe: Add defrag profiling tracepoints

[Matthew Brost <matthew.brost@intel.com>]

Add two tracepoints to profile the page defragmentation worker:

 - xe_bo_defrag_worker: emitted on worker entry and exit with the
   current defrag list count and the bytes processed in the run.
 - xe_bo_defrag_one: emitted per BO with the run budget, the prealloc
   fill ratio (got/want) and the lock-held, lock-wait and prealloc
   durations, plus the bytes consumed and the result.

These break down the cost of a defrag attempt into its locked vs
unlocked phases, making it possible to confirm that the expensive
beneficial-order allocation and cpu cache mode change happen outside
the BO dma-resv lock and that the residual lock-held time is copy-bound
(with the tail dominated by lock-wait behind active rendering).

Cc: Carlos Santa <carlos.santa@intel.com>
Cc: Ryan Neph <ryanneph@google.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Cc: Huang Rui <ray.huang@amd.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Assisted-by: GitHub_Copilot:claude-opus-4.8
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c       | 18 +++++++++-
 drivers/gpu/drm/xe/xe_trace_bo.h | 59 ++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 2f014fc9f988..a01004265349 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1254,7 +1254,9 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo,
 	struct ttm_placement placement;
 	struct ttm_place place;
 	enum ttm_caching tt_caching;
-	unsigned int order, want = 0;
+	unsigned int order, want = 0, got = 0;
+	u64 lock_ns = 0, prealloc_ns = 0, lockwait_ns = 0;
+	ktime_t t0;
 	int ret = 0;
 
 	*consumed = 0;
@@ -1284,6 +1286,7 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo,
 
 	/* Phase 2: preallocate outside the lock; */
 	if (want) {
+		t0 = ktime_get();
 		ret = ttm_pool_prealloc_fill(pool, tt_caching, &pp, want);
 		if (ret || !pp.count) {
 			ret = ret ?: -ENOMEM;
@@ -1291,12 +1294,16 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo,
 					 XE_GT_STATS_ID_DEFRAG_FAILED_COUNT, 1);
 			goto out_err;
 		}
+		prealloc_ns = ktime_to_ns(ktime_sub(ktime_get(), t0));
 	}
 
 	/*
 	 * Phase 3: re-take the lock, re-check, and validate using the prealloc.
 	 */
+	t0 = ktime_get();
 	xe_bo_lock(bo, false);
+	lockwait_ns = ktime_to_ns(ktime_sub(ktime_get(), t0));
+	t0 = ktime_get();
 
 	if (!xe_bo_needs_defrag(bo)) {
 		xe_bo_defrag_remove(bo);
@@ -1350,9 +1357,13 @@ static int xe_bo_defrag_one(struct xe_device *xe, struct xe_bo *bo,
 
 unlock:
 	xe_bo_unlock(bo);
+	lock_ns = ktime_to_ns(ktime_sub(ktime_get(), t0));
+	got = pp.used;
 out_err:
 	ttm_pool_prealloc_fini(pool, &pp);
 out:
+	trace_xe_bo_defrag_one(bo, budget, want, got, lock_ns, prealloc_ns,
+			       lockwait_ns, *consumed, ret);
 	return ret;
 }
 
@@ -1373,6 +1384,9 @@ static void xe_bo_defrag_worker(struct work_struct *w)
 		return;
 	}
 
+	trace_xe_bo_defrag_worker(xe, 0, atomic_read(&xe->mem.defrag.count),
+				  true);
+
 	/*
 	 * Process at most XE_BO_DEFRAG_SIZE_LIMIT bytes of newly (re)allocated
 	 * backing per run rather than draining the whole list in one go. Only
@@ -1479,6 +1493,8 @@ static void xe_bo_defrag_worker(struct work_struct *w)
 
 	xe_pm_runtime_put(xe);
 	drm_dev_exit(idx);
+	trace_xe_bo_defrag_worker(xe, defrag_bytes,
+				  atomic_read(&xe->mem.defrag.count), false);
 }
 
 static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
index 86323cf3be2c..a169a322464b 100644
--- a/drivers/gpu/drm/xe/xe_trace_bo.h
+++ b/drivers/gpu/drm/xe/xe_trace_bo.h
@@ -85,6 +85,65 @@ TRACE_EVENT(xe_bo_move,
 		      __get_str(new_placement_name), __get_str(device_id))
 );
 
+TRACE_EVENT(xe_bo_defrag_worker,
+	    TP_PROTO(struct xe_device *xe, u64 defrag_bytes, int count,
+		     bool enter),
+	    TP_ARGS(xe, defrag_bytes, count, enter),
+	    TP_STRUCT__entry(
+		     __string(dev, dev_name(xe->drm.dev))
+		     __field(u64, defrag_bytes)
+		     __field(int, count)
+		     __field(bool, enter)
+		     ),
+	    TP_fast_assign(
+		   __assign_str(dev);
+		   __entry->defrag_bytes = defrag_bytes;
+		   __entry->count = count;
+		   __entry->enter = enter;
+		   ),
+	    TP_printk("dev=%s %s defrag_bytes=%llu count=%d",
+		      __get_str(dev), __entry->enter ? "enter" : "exit",
+		      __entry->defrag_bytes, __entry->count)
+);
+
+TRACE_EVENT(xe_bo_defrag_one,
+	    TP_PROTO(struct xe_bo *bo, u64 budget, unsigned int prealloc_want,
+		     unsigned int prealloc_got, u64 lock_ns, u64 prealloc_ns,
+		     u64 lockwait_ns, u64 consumed, int ret),
+	    TP_ARGS(bo, budget, prealloc_want, prealloc_got, lock_ns,
+		    prealloc_ns, lockwait_ns, consumed, ret),
+	    TP_STRUCT__entry(
+		     __string(dev, __dev_name_bo(bo))
+		     __field(size_t, size)
+		     __field(u64, budget)
+		     __field(unsigned int, prealloc_want)
+		     __field(unsigned int, prealloc_got)
+		     __field(u64, lock_ns)
+		     __field(u64, prealloc_ns)
+		     __field(u64, lockwait_ns)
+		     __field(u64, consumed)
+		     __field(int, ret)
+		     ),
+	    TP_fast_assign(
+		   __assign_str(dev);
+		   __entry->size = xe_bo_size(bo);
+		   __entry->budget = budget;
+		   __entry->prealloc_want = prealloc_want;
+		   __entry->prealloc_got = prealloc_got;
+		   __entry->lock_ns = lock_ns;
+		   __entry->prealloc_ns = prealloc_ns;
+		   __entry->lockwait_ns = lockwait_ns;
+		   __entry->consumed = consumed;
+		   __entry->ret = ret;
+		   ),
+	    TP_printk("dev=%s size=%zu budget=%llu prealloc=%u/%u lock_us=%llu lockwait_us=%llu prealloc_us=%llu consumed=%llu ret=%d",
+		      __get_str(dev), __entry->size, __entry->budget,
+		      __entry->prealloc_got, __entry->prealloc_want,
+		      __entry->lock_ns / 1000, __entry->lockwait_ns / 1000,
+		      __entry->prealloc_ns / 1000, __entry->consumed,
+		      __entry->ret)
+);
+
 DECLARE_EVENT_CLASS(xe_vma,
 		    TP_PROTO(struct xe_vma *vma),
 		    TP_ARGS(vma),
-- 
2.34.1