Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] drm/xe: Wait on external BO kernel fences in exec IOCTL
@ 2026-07-02 21:58 Matthew Brost
  2026-07-02 22:38 ` ✓ CI.KUnit: success for " Patchwork
                   ` (3 more replies)
  0 siblings, 4 replies; 8+ messages in thread
From: Matthew Brost @ 2026-07-02 21:58 UTC (permalink / raw)
  To: intel-xe; +Cc: stable

Before arming a user job, xe_exec_ioctl() only added the VM's
dma-resv KERNEL slot as a dependency. That slot covers rebinds and
the kernel operations of the VM's private BOs, but not external BOs
(bo->vm == NULL), which carry their kernel operations (evictions,
moves, ...) in their own dma-resv KERNEL slot.

The DMA_RESV_USAGE_KERNEL slot is the cross-driver contract for
memory management operations that must complete before the BO or its
backing store may be used: any accessor is required to wait on the
KERNEL fences before touching the resv. By skipping the external BOs'
KERNEL slots, the exec path violated that contract and could schedule
a user job while a kernel operation on an external BO mapped by the VM
was still in flight, racing against it and potentially reading or
writing memory that was being moved.

Replace the VM-only dependency with an iteration over every object
locked by the exec, adding each object's KERNEL slot as a job
dependency. This covers the VM resv (rebinds and private BOs) as well
as every external BO, mirroring the drm_gpuvm_resv_add_fence() call
that later publishes the job fence to the same set of objects.
Long-running mode continues to skip this, as before.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Assisted-by: GitHub_Copilot:claude-opus-4.8
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_exec.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index e05dabfcd43c..d5293bc33a67 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -292,13 +292,23 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto err_exec;
 	}
 
-	/* Wait behind rebinds */
+	/*
+	 * Wait behind rebinds and any kernel operations (evictions, defrag
+	 * moves, ...) on the VM and all external BOs. The VM's private BOs
+	 * carry their kernel ops in the VM dma-resv KERNEL slot, while each
+	 * external BO carries them in its own dma-resv KERNEL slot; both are
+	 * covered by iterating every object locked by the exec, mirroring the
+	 * drm_gpuvm_resv_add_fence() below.
+	 */
 	if (!xe_vm_in_lr_mode(vm)) {
-		err = xe_sched_job_add_deps(job,
-					    xe_vm_resv(vm),
-					    DMA_RESV_USAGE_KERNEL);
-		if (err)
-			goto err_put_job;
+		struct drm_gem_object *obj;
+
+		drm_exec_for_each_locked_object(exec, obj) {
+			err = xe_sched_job_add_deps(job, obj->resv,
+						    DMA_RESV_USAGE_KERNEL);
+			if (err)
+				goto err_put_job;
+		}
 	}
 
 	for (i = 0; i < num_syncs && !err; i++)
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 8+ messages in thread
end of thread, other threads:[~2026-07-09 21:14 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-02 21:58 [PATCH] drm/xe: Wait on external BO kernel fences in exec IOCTL Matthew Brost
2026-07-02 22:38 ` ✓ CI.KUnit: success for " Patchwork
2026-07-02 23:19 ` ✓ Xe.CI.BAT: " Patchwork
2026-07-03  8:45 ` [PATCH] " Matthew Auld
2026-07-09 11:01   ` Thomas Hellström
2026-07-09 19:02     ` Matthew Brost
2026-07-09 21:14       ` Thomas Hellström
2026-07-03 16:44 ` ✗ Xe.CI.FULL: failure for " Patchwork

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