Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v2] drm/xe/xe_guc: Dynamically decide g2g buffer owner
@ 2025-10-28 16:00 Jonathan Cavitt
  2025-10-28 16:19 ` Michal Wajdeczko
                   ` (4 more replies)
  0 siblings, 5 replies; 7+ messages in thread
From: Jonathan Cavitt @ 2025-10-28 16:00 UTC (permalink / raw)
  To: intel-xe
  Cc: saurabhg.gupta, alex.zuo, jonathan.cavitt, matthew.d.roper,
	michal.wajdeczko, daniele.ceraolospurio

On today's driver, xe_device_get_gt(xe, 0); can never return NULL.
Hardware-wise there's always at least one tile, and every tilie has a
primary GT.  If something went wrong during init of tile or GT and we
couldn't create/initialize the structures, then we already aborted the
device probe immediately and we'll never get further on to places in the
code that would be chasing a NULL pointer.

However, there's currently ongoing work to allow the primary GT to be
disabled via configfs for debugging purposes.  Once that lands, it will
be possible for this query to return a NULL pointer.  This can cause
problems in guc_g2g_alloc, as this process currently relies on the
primary GT always being present.

Instead of making the primary GT the g2g buffer owner, make the first
GuC passed to guc_g2g_alloc the g2g buffer owner.  This requires keeping
track of the g2g buffer owner in the xe device so each GuC can know if
it's the owner or not during initialization.

v2:
- Update the kunit tests to clear and reset the g2g_owner variable as
  needed (Daniele)

Suggested-by: Matt Roper <matthew.d.roper@intel.com>
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c | 2 ++
 drivers/gpu/drm/xe/xe_device_types.h       | 4 ++++
 drivers/gpu/drm/xe/xe_guc.c                | 9 ++++++---
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c b/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c
index 3b213fcae916..6446232422e2 100644
--- a/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_guc_g2g_test.c
@@ -358,6 +358,7 @@ static void g2g_distribute(struct kunit *test, struct xe_device *xe, struct xe_b
 	root_gt = xe_device_get_gt(xe, 0);
 	root_gt->uc.guc.g2g.bo = bo;
 	root_gt->uc.guc.g2g.owned = true;
+	xe->g2g_owner = &root_gt->uc.guc;
 	kunit_info(test, "[%d.%d] Assigned 0x%p\n", gt_to_tile(root_gt)->id, root_gt->info.id, bo);
 
 	for_each_gt(gt, xe, i) {
@@ -447,6 +448,7 @@ static void g2g_free(struct kunit *test, struct xe_device *xe)
 
 		gt->uc.guc.g2g.bo = NULL;
 	}
+	xe->g2g_owner = NULL;
 }
 
 static void g2g_stop(struct kunit *test, struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index af0ce275b032..91ec9a295226 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -38,6 +38,7 @@ struct dram_info;
 struct intel_display;
 struct intel_dg_nvm_dev;
 struct xe_ggtt;
+struct xe_guc;
 struct xe_i2c;
 struct xe_pat_ops;
 struct xe_pxp;
@@ -628,6 +629,9 @@ struct xe_device {
 	atomic_t g2g_test_count;
 #endif
 
+	/** @g2g_owner: Pointer to the GuC that is the owner of the g2g buffer */
+	struct xe_guc *g2g_owner;
+
 	/* private: */
 
 #if IS_ENABLED(CONFIG_DRM_XE_DISPLAY)
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index ecc3e091b89e..a3a0961456d0 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -468,9 +468,8 @@ static int guc_g2g_alloc(struct xe_guc *guc)
 	if (guc->g2g.bo)
 		return 0;
 
-	if (gt->info.id != 0) {
-		struct xe_gt *root_gt = xe_device_get_gt(xe, 0);
-		struct xe_guc *root_guc = &root_gt->uc.guc;
+	if (xe->g2g_owner) {
+		struct xe_guc *root_guc = xe->g2g_owner;
 		struct xe_bo *bo;
 
 		bo = xe_bo_get(root_guc->g2g.bo);
@@ -495,6 +494,7 @@ static int guc_g2g_alloc(struct xe_guc *guc)
 	xe_map_memset(xe, &bo->vmap, 0, 0, g2g_size);
 	guc->g2g.bo = bo;
 	guc->g2g.owned = true;
+	xe->g2g_owner = guc;
 
 	return 0;
 }
@@ -507,6 +507,9 @@ static void guc_g2g_fini(struct xe_guc *guc)
 	/* Unpinning the owned object is handled by generic shutdown */
 	if (!guc->g2g.owned)
 		xe_bo_put(guc->g2g.bo);
+	/* g2g owner is no longer valid.  Mark as NULL in xe device */
+	else
+		guc_to_xe(guc)->g2g_owner = NULL;
 
 	guc->g2g.bo = NULL;
 }
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 7+ messages in thread
end of thread, other threads:[~2025-10-30 16:21 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-10-28 16:00 [PATCH v2] drm/xe/xe_guc: Dynamically decide g2g buffer owner Jonathan Cavitt
2025-10-28 16:19 ` Michal Wajdeczko
2025-10-28 16:21   ` Cavitt, Jonathan
2025-10-28 19:16 ` ✓ CI.KUnit: success for drm/xe/xe_guc: Dynamically decide g2g buffer owner (rev2) Patchwork
2025-10-28 19:54 ` ✓ Xe.CI.BAT: " Patchwork
2025-10-29  5:57 ` ✗ Xe.CI.Full: failure " Patchwork
2025-10-30 16:21 ` [PATCH v2] drm/xe/xe_guc: Dynamically decide g2g buffer owner Daniele Ceraolo Spurio

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox