[Intel-xe] [PATCH] drm/xe/engine: add missing rpm for bind engines

[Matthew Auld]

Bind engines need to use the migration vm, however we don't have any rpm
for such a vm, otherwise the kernel would prevent rpm suspend-resume.
There are two issues here, first is the actual engine create which needs
to touch the lrc, but since that is in VRAM we trigger loads of missing
mem_access asserts. The second issue is when destroying the actual
engine, which requires GuC CT to deregister the context.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/499
Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
Signed-off-by: Matthew Auld <matthew.auld at intel.com>
---
 drivers/gpu/drm/xe/xe_engine.c       | 20 ++++++++++++++++++++
 drivers/gpu/drm/xe/xe_engine_types.h |  1 +
 2 files changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_engine.c b/drivers/gpu/drm/xe/xe_engine.c
index 59e0a9e085ba..dba71f53e53e 100644
--- a/drivers/gpu/drm/xe/xe_engine.c
+++ b/drivers/gpu/drm/xe/xe_engine.c
@@ -76,6 +76,17 @@ static struct xe_engine *__xe_engine_create(struct xe_device *xe,
 	if (err)
 		goto err_lrc;
 
+	/*
+	 * Normally the user vm holds an rpm ref to keep the device awake, and
+	 * the context holds a ref for the vm, however for some engines we use
+	 * the kernels migrate vm underneath which offers no such rpm ref. Make
+	 * sure we keep a ref here, so we can perform GuC CT actions when
+	 * needed. Caller is expected to have already grabbed the rpm ref
+	 * outside any sensitive locks.
+	 */
+	if (e->flags & ENGINE_FLAG_HOLD_RPM)
+		drm_WARN_ON(&xe->drm, !xe_device_mem_access_get_if_ongoing(xe));
+
 	return e;
 
 err_lrc:
@@ -152,6 +163,8 @@ void xe_engine_fini(struct xe_engine *e)
 		xe_lrc_finish(e->lrc + i);
 	if (e->vm)
 		xe_vm_put(e->vm);
+	if (e->flags & ENGINE_FLAG_HOLD_RPM)
+		xe_device_mem_access_put(gt_to_xe(e->gt));
 
 	kfree(e);
 }
@@ -560,14 +573,21 @@ int xe_engine_create_ioctl(struct drm_device *dev, void *data,
 			if (XE_IOCTL_DBG(xe, !hwe))
 				return -EINVAL;
 
+			/* The migration vm doesn't hold rpm ref */
+			xe_device_mem_access_get(xe);
+
 			migrate_vm = xe_migrate_get_vm(gt_to_tile(gt)->migrate);
 			new = xe_engine_create(xe, migrate_vm, logical_mask,
 					       args->width, hwe,
+					       ENGINE_FLAG_HOLD_RPM |
 					       ENGINE_FLAG_PERSISTENT |
 					       ENGINE_FLAG_VM |
 					       (id ?
 					       ENGINE_FLAG_BIND_ENGINE_CHILD :
 					       0));
+
+			xe_device_mem_access_put(xe); /* now held by engine */
+
 			xe_vm_put(migrate_vm);
 			if (IS_ERR(new)) {
 				err = PTR_ERR(new);
diff --git a/drivers/gpu/drm/xe/xe_engine_types.h b/drivers/gpu/drm/xe/xe_engine_types.h
index 36bfaeec23f4..a3867e4db0bb 100644
--- a/drivers/gpu/drm/xe/xe_engine_types.h
+++ b/drivers/gpu/drm/xe/xe_engine_types.h
@@ -59,6 +59,7 @@ struct xe_engine {
 #define ENGINE_FLAG_VM			BIT(4)
 #define ENGINE_FLAG_BIND_ENGINE_CHILD	BIT(5)
 #define ENGINE_FLAG_WA			BIT(6)
+#define ENGINE_FLAG_HOLD_RPM		BIT(7)
 
 	/**
 	 * @flags: flags for this engine, should statically setup aside from ban
-- 
2.41.0