[RFC,11/17] drm/amdkfd: CRIU restore queue doorbell id

Commit Message

Felix Kuehling May 1, 2021, 1:57 a.m. UTC

From: David Yat Sin <[e-mail]>

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 <[e-mail]>
Change-Id: I6a79de1f8c760d5a9d28e7951740296f2f8796a7
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c      |  1 +
 .../drm/amd/amdkfd/kfd_device_queue_manager.c | 58 +++++++++++++------
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h         |  1 +
 3 files changed, 41 insertions(+), 19 deletions(-)

Patch

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index afcbdae436fa..130ab100abb2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2153,6 +2153,7 @@  int criu_restore_queue(struct kfd_process *p,
 
 	qrd->qid = q_bucket->q_id;
 	qrd->sdma_id = q_bucket->sdma_id;
+	qrd->doorbell_id = q_bucket->doorbell_id;
 
 	ret = pqm_create_queue(&p->pqm, dev, NULL, &qp, &queue_id, qrd, NULL);
 	if (ret) {
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 cabdfbacce37..56250c0b5ca0 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 +153,11 @@  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 +165,9 @@  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 +176,38 @@  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 =
@@ -343,7 +363,7 @@  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, qrd ? &qrd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_hqd;
 
@@ -1314,7 +1334,7 @@  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, qrd ? &qrd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index bd518340c38c..a4a0713ca9a3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -472,6 +472,7 @@  enum KFD_QUEUE_PRIORITY {
 struct queue_restore_data {
 	uint32_t qid;
 	uint32_t sdma_id;
+	uint32_t doorbell_id;
 };
 
 struct queue_properties {