'drm/xe/hw_engine_group: Register hw engine group's exec queues

Add helpers to safely add and delete the exec queues attached to a hw
engine group, and make use them at the time of creation and destruction of
the exec queues. Keeping track of them is required to control the
execution mode of the hw engine group.

v2: Improve error handling and robustness, suspend exec queues created in
    fault mode if group in dma-fence mode, init queue link (Matt Brost)

v3: Delete queue from hw engine group when it is destroyed by the user,
    also clean up at the time of closing the file in case the user did
    not destroy the queue

v4: Use correct list when checking if empty, do not add the queue if VM
    is in xe_vm_in_preempt_fence_mode (Matt Brost)

v5: Remove unrelated newline, add checks and asserts for group, unwind on
    suspend failure (Matt Brost)

Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-4-francois.dugast@intel.com

5 files changed, 86 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 206328387150..b6db7e082d88 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -37,6 +37,7 @@
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_guc.h"
+#include "xe_hw_engine_group.h"
 #include "xe_hwmon.h"
 #include "xe_irq.h"
 #include "xe_memirq.h"
@@ -165,6 +166,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 	 * vm->lock taken during xe_exec_queue_kill().
 	 */
 	xa_for_each(&xef->exec_queue.xa, idx, q) {
+		if (q->vm && q->hwe->hw_engine_group)
+			xe_hw_engine_group_del_exec_queue(q->hwe->hw_engine_group, q);
 		xe_exec_queue_kill(q);
 		xe_exec_queue_put(q);
 	}
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 7f0b33098182..ebc80add10ac 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -14,6 +14,7 @@
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_hw_engine_class_sysfs.h"
+#include "xe_hw_engine_group.h"
 #include "xe_hw_fence.h"
 #include "xe_lrc.h"
 #include "xe_macros.h"
@@ -73,6 +74,7 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 	q->ops = gt->exec_queue_ops;
 	INIT_LIST_HEAD(&q->lr.link);
 	INIT_LIST_HEAD(&q->multi_gt_link);
+	INIT_LIST_HEAD(&q->hw_engine_group_link);
 
 	q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
 	q->sched_props.preempt_timeout_us =
@@ -624,6 +626,12 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 			if (XE_IOCTL_DBG(xe, err))
 				goto put_exec_queue;
 		}
+
+		if (q->vm && q->hwe->hw_engine_group) {
+			err = xe_hw_engine_group_add_exec_queue(q->hwe->hw_engine_group, q);
+			if (err)
+				goto put_exec_queue;
+		}
 	}
 
 	mutex_lock(&xef->exec_queue.lock);
@@ -815,6 +823,9 @@ int xe_exec_queue_destroy_ioctl(struct drm_device *dev, void *data,
 	if (XE_IOCTL_DBG(xe, !q))
 		return -ENOENT;
 
+	if (q->vm && q->hwe->hw_engine_group)
+		xe_hw_engine_group_del_exec_queue(q->hwe->hw_engine_group, q);
+
 	xe_exec_queue_kill(q);
 
 	trace_xe_exec_queue_close(q);
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 1408b02eea53..315f874426bd 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -142,6 +142,8 @@ struct xe_exec_queue {
 	 * Protected by @vm's resv. Unused if @vm == NULL.
 	 */
 	u64 tlb_flush_seqno;
+	/** @hw_engine_group_link: link into exec queues in the same hw engine group */
+	struct list_head hw_engine_group_link;
 	/** @lrc: logical ring context for this exec queue */
 	struct xe_lrc *lrc[];
 };
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c
index 1d109c08c7a6..b362af7ffab5 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c
@@ -5,9 +5,12 @@
 
 #include <drm/drm_managed.h>
 
+#include "xe_assert.h"
 #include "xe_device.h"
+#include "xe_exec_queue.h"
 #include "xe_gt.h"
 #include "xe_hw_engine_group.h"
+#include "xe_vm.h"
 
 static void
 hw_engine_group_free(struct drm_device *drm, void *arg)
@@ -100,3 +103,66 @@ err_group_rcs_ccs:
 
 	return err;
 }
+
+/**
+ * xe_hw_engine_group_add_exec_queue() - Add an exec queue to a hw engine group
+ * @group: The hw engine group
+ * @q: The exec_queue
+ *
+ * Return: 0 on success,
+ *	    -EINTR if the lock could not be acquired
+ */
+int xe_hw_engine_group_add_exec_queue(struct xe_hw_engine_group *group, struct xe_exec_queue *q)
+{
+	int err;
+	struct xe_device *xe = gt_to_xe(q->gt);
+
+	xe_assert(xe, group);
+	xe_assert(xe, !(q->flags & EXEC_QUEUE_FLAG_VM));
+	xe_assert(xe, q->vm);
+
+	if (xe_vm_in_preempt_fence_mode(q->vm))
+		return 0;
+
+	err = down_write_killable(&group->mode_sem);
+	if (err)
+		return err;
+
+	if (xe_vm_in_fault_mode(q->vm) && group->cur_mode == EXEC_MODE_DMA_FENCE) {
+		q->ops->suspend(q);
+		err = q->ops->suspend_wait(q);
+		if (err)
+			goto err_suspend;
+
+		queue_work(group->resume_wq, &group->resume_work);
+	}
+
+	list_add(&q->hw_engine_group_link, &group->exec_queue_list);
+	up_write(&group->mode_sem);
+
+	return 0;
+
+err_suspend:
+	up_write(&group->mode_sem);
+	return err;
+}
+
+/**
+ * xe_hw_engine_group_del_exec_queue() - Delete an exec queue from a hw engine group
+ * @group: The hw engine group
+ * @q: The exec_queue
+ */
+void xe_hw_engine_group_del_exec_queue(struct xe_hw_engine_group *group, struct xe_exec_queue *q)
+{
+	struct xe_device *xe = gt_to_xe(q->gt);
+
+	xe_assert(xe, group);
+	xe_assert(xe, q->vm);
+
+	down_write(&group->mode_sem);
+
+	if (!list_empty(&q->hw_engine_group_link))
+		list_del(&q->hw_engine_group_link);
+
+	up_write(&group->mode_sem);
+}
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.h b/drivers/gpu/drm/xe/xe_hw_engine_group.h
index c2648f87f7ef..857a83787504 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.h
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.h
@@ -9,8 +9,12 @@
 #include "xe_hw_engine_group_types.h"
 
 struct drm_device;
+struct xe_exec_queue;
 struct xe_gt;
 
 int xe_hw_engine_setup_groups(struct xe_gt *gt);
 
+int xe_hw_engine_group_add_exec_queue(struct xe_hw_engine_group *group, struct xe_exec_queue *q);
+void xe_hw_engine_group_del_exec_queue(struct xe_hw_engine_group *group, struct xe_exec_queue *q);
+
 #endif