[v4,11/24] drm/amdkfd: CRIU restore sdma id for queues

Commit Message

Rajneesh Bhardwaj Dec. 23, 2021, 12:36 a.m. UTC

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

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

Signed-off-by: David Yat Sin <[e-mail]>

---
 .../drm/amd/amdkfd/kfd_device_queue_manager.c | 48 ++++++++++++++-----
 .../drm/amd/amdkfd/kfd_device_queue_manager.h |  3 +-
 .../amd/amdkfd/kfd_process_queue_manager.c    |  4 +-
 3 files changed, 40 insertions(+), 15 deletions(-)

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 62fe28244a80..7e49f70b81b9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -58,7 +58,7 @@  static inline void deallocate_hqd(struct device_queue_manager *dqm,
 				struct queue *q);
 static int allocate_hqd(struct device_queue_manager *dqm, struct queue *q);
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
-				struct queue *q);
+				struct queue *q, const uint32_t *restore_sdma_id);
 static void kfd_process_hw_exception(struct work_struct *work);
 
 static inline
@@ -308,7 +308,8 @@  static void deallocate_vmid(struct device_queue_manager *dqm,
 
 static int create_queue_nocpsch(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd)
+				struct qcm_process_device *qpd,
+				const struct kfd_criu_queue_priv_data *qd)
 {
 	struct mqd_manager *mqd_mgr;
 	int retval;
@@ -348,7 +349,7 @@  static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			q->pipe, q->queue);
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
-		retval = allocate_sdma_queue(dqm, q);
+		retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
 		if (retval)
 			goto deallocate_vmid;
 		dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
@@ -1040,7 +1041,7 @@  static void pre_reset(struct device_queue_manager *dqm)
 }
 
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
-				struct queue *q)
+				struct queue *q, const uint32_t *restore_sdma_id)
 {
 	int bit;
 
@@ -1050,9 +1051,21 @@  static int allocate_sdma_queue(struct device_queue_manager *dqm,
 			return -ENOMEM;
 		}
 
-		bit = __ffs64(dqm->sdma_bitmap);
-		dqm->sdma_bitmap &= ~(1ULL << bit);
-		q->sdma_id = bit;
+		if (restore_sdma_id) {
+			/* Re-use existing sdma_id */
+			if (!(dqm->sdma_bitmap & (1ULL << *restore_sdma_id))) {
+				pr_err("SDMA queue already in use\n");
+				return -EBUSY;
+			}
+			dqm->sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+			q->sdma_id = *restore_sdma_id;
+		} else {
+			/* Find first available sdma_id */
+			bit = __ffs64(dqm->sdma_bitmap);
+			dqm->sdma_bitmap &= ~(1ULL << bit);
+			q->sdma_id = bit;
+		}
+
 		q->properties.sdma_engine_id = q->sdma_id %
 				get_num_sdma_engines(dqm);
 		q->properties.sdma_queue_id = q->sdma_id /
@@ -1062,9 +1075,19 @@  static int allocate_sdma_queue(struct device_queue_manager *dqm,
 			pr_err("No more XGMI SDMA queue to allocate\n");
 			return -ENOMEM;
 		}
-		bit = __ffs64(dqm->xgmi_sdma_bitmap);
-		dqm->xgmi_sdma_bitmap &= ~(1ULL << bit);
-		q->sdma_id = bit;
+		if (restore_sdma_id) {
+			/* Re-use existing sdma_id */
+			if (!(dqm->xgmi_sdma_bitmap & (1ULL << *restore_sdma_id))) {
+				pr_err("SDMA queue already in use\n");
+				return -EBUSY;
+			}
+			dqm->xgmi_sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+			q->sdma_id = *restore_sdma_id;
+		} else {
+			bit = __ffs64(dqm->xgmi_sdma_bitmap);
+			dqm->xgmi_sdma_bitmap &= ~(1ULL << bit);
+			q->sdma_id = bit;
+		}
 		/* sdma_engine_id is sdma id including
 		 * both PCIe-optimized SDMAs and XGMI-
 		 * optimized SDMAs. The calculation below
@@ -1293,7 +1316,8 @@  static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
-			struct qcm_process_device *qpd)
+			struct qcm_process_device *qpd,
+			const struct kfd_criu_queue_priv_data *qd)
 {
 	int retval;
 	struct mqd_manager *mqd_mgr;
@@ -1308,7 +1332,7 @@  static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
 		dqm_lock(dqm);
-		retval = allocate_sdma_queue(dqm, q);
+		retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
 		dqm_unlock(dqm);
 		if (retval)
 			goto out;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 499fc0ea387f..6fa43215e3e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -86,7 +86,8 @@  struct device_process_node {
 struct device_queue_manager_ops {
 	int	(*create_queue)(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd);
+				struct qcm_process_device *qpd,
+				const struct kfd_criu_queue_priv_data *qd);
 
 	int	(*destroy_queue)(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 275aeebc58fa..25cf97d97d87 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -273,7 +273,7 @@  int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;
-		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
 		print_queue(q);
 		break;
 
@@ -293,7 +293,7 @@  int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;
-		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data);
 		print_queue(q);
 		break;
 	case KFD_QUEUE_TYPE_DIQ: