diff mbox series

[v4,12/24] drm/amdkfd: CRIU restore queue doorbell id

Message ID 20211223003711.13064-13-rajneesh.bhardwaj@amd.com (mailing list archive)
State New, archived
Headers show
Series CHECKPOINT RESTORE WITH ROCm | expand

Commit Message

Rajneesh Bhardwaj Dec. 23, 2021, 12:36 a.m. UTC 
From: David Yat Sin <david.yatsin@amd.com>

When re-creating queues during CRIU restore, restore the queue with the
same doorbell id value used during CRIU dump.

Signed-off-by: David Yat Sin <david.yatsin@amd.com>

---
 .../drm/amd/amdkfd/kfd_device_queue_manager.c | 60 +++++++++++++------
 1 file changed, 41 insertions(+), 19 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 7e49f70b81b9..a0f5b8533a03 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -153,7 +153,13 @@  static void decrement_queue_count(struct device_queue_manager *dqm,
 		dqm->active_cp_queue_count--;
 }
 
-static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
+/*
+ * Allocate a doorbell ID to this queue.
+ * If doorbell_id is passed in, make sure requested ID is valid then allocate it.
+ */
+static int allocate_doorbell(struct qcm_process_device *qpd,
+			     struct queue *q,
+			     uint32_t const *restore_id)
 {
 	struct kfd_dev *dev = qpd->dqm->dev;
 
@@ -161,6 +167,10 @@  static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		/* On pre-SOC15 chips we need to use the queue ID to
 		 * preserve the user mode ABI.
 		 */
+
+		if (restore_id && *restore_id != q->properties.queue_id)
+			return -EINVAL;
+
 		q->doorbell_id = q->properties.queue_id;
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 			q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
@@ -169,25 +179,37 @@  static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		 * The doobell index distance between RLC (2*i) and (2*i+1)
 		 * for a SDMA engine is 512.
 		 */
-		uint32_t *idx_offset =
-				dev->shared_resources.sdma_doorbell_idx;
 
-		q->doorbell_id = idx_offset[q->properties.sdma_engine_id]
-			+ (q->properties.sdma_queue_id & 1)
-			* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
-			+ (q->properties.sdma_queue_id >> 1);
+		uint32_t *idx_offset = dev->shared_resources.sdma_doorbell_idx;
+		uint32_t valid_id = idx_offset[q->properties.sdma_engine_id]
+						+ (q->properties.sdma_queue_id & 1)
+						* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
+						+ (q->properties.sdma_queue_id >> 1);
+
+		if (restore_id && *restore_id != valid_id)
+			return -EINVAL;
+		q->doorbell_id = valid_id;
 	} else {
-		/* For CP queues on SOC15 reserve a free doorbell ID */
-		unsigned int found;
-
-		found = find_first_zero_bit(qpd->doorbell_bitmap,
-					    KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
-		if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
-			pr_debug("No doorbells available");
-			return -EBUSY;
+		/* For CP queues on SOC15 */
+		if (restore_id) {
+			/* make sure that ID is free  */
+			if (__test_and_set_bit(*restore_id, qpd->doorbell_bitmap))
+				return -EINVAL;
+
+			q->doorbell_id = *restore_id;
+		} else {
+			/* or reserve a free doorbell ID */
+			unsigned int found;
+
+			found = find_first_zero_bit(qpd->doorbell_bitmap,
+						KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
+			if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
+				pr_debug("No doorbells available");
+				return -EBUSY;
+			}
+			set_bit(found, qpd->doorbell_bitmap);
+			q->doorbell_id = found;
 		}
-		set_bit(found, qpd->doorbell_bitmap);
-		q->doorbell_id = found;
 	}
 
 	q->properties.doorbell_off =
@@ -355,7 +377,7 @@  static int create_queue_nocpsch(struct device_queue_manager *dqm,
 		dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
 	}
 
-	retval = allocate_doorbell(qpd, q);
+	retval = allocate_doorbell(qpd, q, qd ? &qd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_hqd;
 
@@ -1338,7 +1360,7 @@  static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			goto out;
 	}
 
-	retval = allocate_doorbell(qpd, q);
+	retval = allocate_doorbell(qpd, q, qd ? &qd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_sdma_queue;