drm/amdkfd: Introduce XGMI SDMA queue type

Existing QUEUE_TYPE_SDMA means PCIe optimized SDMA queues.
Introduce a new QUEUE_TYPE_SDMA_XGMI, which is optimized
for non-PCIe transfer such as XGMI.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

9 files changed, 128 insertions, 36 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 3ccaa38779ea..38ae53fe8182 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -213,6 +213,8 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 		q_properties->type = KFD_QUEUE_TYPE_COMPUTE;
 	else if (args->queue_type == KFD_IOC_QUEUE_TYPE_SDMA)
 		q_properties->type = KFD_QUEUE_TYPE_SDMA;
+	else if (args->queue_type == KFD_IOC_QUEUE_TYPE_SDMA_XGMI)
+		q_properties->type = KFD_QUEUE_TYPE_SDMA_XGMI;
 	else
 		return -ENOTSUPP;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 8202a5db3a35..1368b41cb92b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -54,6 +54,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -71,6 +72,7 @@ static const struct kfd_device_info carrizo_device_info = {
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -87,6 +89,7 @@ static const struct kfd_device_info raven_device_info = {
 	.needs_iommu_device = true,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 1,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 #endif
@@ -105,6 +108,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -121,6 +125,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -137,6 +142,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -153,6 +159,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -170,6 +177,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -186,6 +194,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -202,6 +211,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -218,6 +228,7 @@ static const struct kfd_device_info polaris12_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -234,6 +245,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -250,6 +262,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -266,6 +279,7 @@ static const struct kfd_device_info vega12_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 2,
 };
 
@@ -282,6 +296,7 @@ static const struct kfd_device_info vega20_device_info = {
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
 };
 
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 d41045d3fc3a..1562590d837e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -60,14 +60,14 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd);
 
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
-				unsigned int sdma_queue_id);
+				struct queue *q);
 
 static void kfd_process_hw_exception(struct work_struct *work);
 
 static inline
 enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type)
 {
-	if (type == KFD_QUEUE_TYPE_SDMA)
+	if (type == KFD_QUEUE_TYPE_SDMA || type == KFD_QUEUE_TYPE_SDMA_XGMI)
 		return KFD_MQD_TYPE_SDMA;
 	return KFD_MQD_TYPE_CP;
 }
@@ -107,12 +107,23 @@ static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm)
 	return dqm->dev->device_info->num_sdma_engines;
 }
 
+static unsigned int get_num_xgmi_sdma_engines(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_xgmi_sdma_engines;
+}
+
 unsigned int get_num_sdma_queues(struct device_queue_manager *dqm)
 {
 	return dqm->dev->device_info->num_sdma_engines
 			* dqm->dev->device_info->num_sdma_queues_per_engine;
 }
 
+unsigned int get_num_xgmi_sdma_queues(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_xgmi_sdma_engines
+			* dqm->dev->device_info->num_sdma_queues_per_engine;
+}
+
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
@@ -133,7 +144,8 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		 * preserve the user mode ABI.
 		 */
 		q->doorbell_id = q->properties.queue_id;
-	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+			q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
 		/* For SDMA queues on SOC15 with 8-byte doorbell, use static
 		 * doorbell assignments based on the engine and queue id.
 		 * The doobell index distance between RLC (2*i) and (2*i+1)
@@ -174,7 +186,8 @@ static void deallocate_doorbell(struct qcm_process_device *qpd,
 	struct kfd_dev *dev = qpd->dqm->dev;
 
 	if (!KFD_IS_SOC15(dev->device_info->asic_family) ||
-	    q->properties.type == KFD_QUEUE_TYPE_SDMA)
+	    q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+	    q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
 		return;
 
 	old = test_and_clear_bit(q->doorbell_id, qpd->doorbell_bitmap);
@@ -289,7 +302,8 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE)
 		retval = create_compute_queue_nocpsch(dqm, q, qpd);
-	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
+	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+			q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
 		retval = create_sdma_queue_nocpsch(dqm, q, qpd);
 	else
 		retval = -EINVAL;
@@ -307,6 +321,8 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		dqm->sdma_queue_count++;
+	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
+		dqm->xgmi_sdma_queue_count++;
 
 	/*
 	 * Unconditionally increment this counter, regardless of the queue's
@@ -430,7 +446,10 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 		deallocate_hqd(dqm, q);
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		dqm->sdma_queue_count--;
-		deallocate_sdma_queue(dqm, q->sdma_id);
+		deallocate_sdma_queue(dqm, q);
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+		dqm->xgmi_sdma_queue_count--;
+		deallocate_sdma_queue(dqm, q);
 	} else {
 		pr_debug("q->properties.type %d is invalid\n",
 				q->properties.type);
@@ -521,7 +540,8 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		}
 	} else if (prev_active &&
 		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
-		    q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+		    q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+		    q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
 		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
@@ -548,7 +568,8 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		retval = map_queues_cpsch(dqm);
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
-		  q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+		  q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+		  q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
 		if (WARN(q->process->mm != current->mm,
 			 "should only run in user thread"))
 			retval = -EFAULT;
@@ -840,6 +861,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->next_pipe_to_allocate = 0;
 	dqm->sdma_queue_count = 0;
+	dqm->xgmi_sdma_queue_count = 0;
 
 	for (pipe = 0; pipe < get_pipes_per_mec(dqm); pipe++) {
 		int pipe_offset = pipe * get_queues_per_pipe(dqm);
@@ -852,6 +874,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 
 	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
 	dqm->sdma_bitmap = (1ULL << get_num_sdma_queues(dqm)) - 1;
+	dqm->xgmi_sdma_bitmap = (1ULL << get_num_xgmi_sdma_queues(dqm)) - 1;
 
 	return 0;
 }
@@ -886,17 +909,34 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 {
 	int bit;
 
-	if (dqm->sdma_bitmap == 0)
-		return -ENOMEM;
-
-	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 / get_num_sdma_engines(dqm);
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+		if (dqm->sdma_bitmap == 0)
+			return -ENOMEM;
+		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 /
+				get_num_sdma_engines(dqm);
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+		if (dqm->xgmi_sdma_bitmap == 0)
+			return -ENOMEM;
+		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
+		 * assumes the first N engines are always
+		 * PCIe-optimized ones
+		 */
+		q->properties.sdma_engine_id = get_num_sdma_engines(dqm) +
+				q->sdma_id % get_num_xgmi_sdma_engines(dqm);
+		q->properties.sdma_queue_id = q->sdma_id /
+				get_num_xgmi_sdma_engines(dqm);
+	}
 
-	pr_debug("SDMA id is:    %d\n", q->sdma_id);
 	pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
 	pr_debug("SDMA queue id: %d\n", q->properties.sdma_queue_id);
 
@@ -904,11 +944,17 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 }
 
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
-				unsigned int sdma_id)
+				struct queue *q)
 {
-	if (sdma_id >= get_num_sdma_queues(dqm))
-		return;
-	dqm->sdma_bitmap |= (1ULL << sdma_id);
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+		if (q->sdma_id >= get_num_sdma_queues(dqm))
+			return;
+		dqm->sdma_bitmap |= (1ULL << q->sdma_id);
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+		if (q->sdma_id >= get_num_xgmi_sdma_queues(dqm))
+			return;
+		dqm->xgmi_sdma_bitmap |= (1ULL << q->sdma_id);
+	}
 }
 
 static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
@@ -946,7 +992,7 @@ out_uninit_mqd:
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
-	deallocate_sdma_queue(dqm, q->sdma_id);
+	deallocate_sdma_queue(dqm, q);
 
 	return retval;
 }
@@ -1004,8 +1050,10 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
+	dqm->xgmi_sdma_queue_count = 0;
 	dqm->active_runlist = false;
 	dqm->sdma_bitmap = (1ULL << get_num_sdma_queues(dqm)) - 1;
+	dqm->xgmi_sdma_bitmap = (1ULL << get_num_xgmi_sdma_queues(dqm)) - 1;
 
 	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
@@ -1127,7 +1175,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		goto out;
 	}
 
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
 		retval = allocate_sdma_queue(dqm, q);
 		if (retval)
 			goto out;
@@ -1167,6 +1216,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		dqm->sdma_queue_count++;
+	else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
+		dqm->xgmi_sdma_queue_count++;
 	/*
 	 * Unconditionally increment this counter, regardless of the queue's
 	 * type or whether the queue is active.
@@ -1182,8 +1233,9 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
-	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
-		deallocate_sdma_queue(dqm, q->sdma_id);
+	if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
+		deallocate_sdma_queue(dqm, q);
 out:
 	return retval;
 }
@@ -1216,7 +1268,8 @@ static int unmap_sdma_queues(struct device_queue_manager *dqm)
 {
 	int i, retval = 0;
 
-	for (i = 0; i < dqm->dev->device_info->num_sdma_engines; i++) {
+	for (i = 0; i < dqm->dev->device_info->num_sdma_engines +
+		dqm->dev->device_info->num_xgmi_sdma_engines; i++) {
 		retval = pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_SDMA,
 			KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, false, i);
 		if (retval)
@@ -1258,10 +1311,10 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	if (!dqm->active_runlist)
 		return retval;
 
-	pr_debug("Before destroying queues, sdma queue count is : %u\n",
-		dqm->sdma_queue_count);
+	pr_debug("Before destroying queues, sdma queue count is : %u, xgmi sdma queue count is : %u\n",
+		dqm->sdma_queue_count, dqm->xgmi_sdma_queue_count);
 
-	if (dqm->sdma_queue_count > 0)
+	if (dqm->sdma_queue_count > 0 || dqm->xgmi_sdma_queue_count)
 		unmap_sdma_queues(dqm);
 
 	retval = pm_send_unmap_queue(&dqm->packets, KFD_QUEUE_TYPE_COMPUTE,
@@ -1333,7 +1386,10 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 		dqm->sdma_queue_count--;
-		deallocate_sdma_queue(dqm, q->sdma_id);
+		deallocate_sdma_queue(dqm, q);
+	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+		dqm->xgmi_sdma_queue_count--;
+		deallocate_sdma_queue(dqm, q);
 	}
 
 	list_del(&q->list);
@@ -1550,7 +1606,10 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
 			dqm->sdma_queue_count--;
-			deallocate_sdma_queue(dqm, q->sdma_id);
+			deallocate_sdma_queue(dqm, q);
+		} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+			dqm->xgmi_sdma_queue_count--;
+			deallocate_sdma_queue(dqm, q);
 		}
 
 		if (q->properties.is_active)
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 3742fd340ec3..88b4c007696e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -181,10 +181,12 @@ struct device_queue_manager {
 	unsigned int		processes_count;
 	unsigned int		queue_count;
 	unsigned int		sdma_queue_count;
+	unsigned int		xgmi_sdma_queue_count;
 	unsigned int		total_queue_count;
 	unsigned int		next_pipe_to_allocate;
 	unsigned int		*allocated_queues;
 	uint64_t		sdma_bitmap;
+	uint64_t		xgmi_sdma_bitmap;
 	unsigned int		vmid_bitmap;
 	uint64_t		pipelines_addr;
 	struct kfd_mem_obj	*pipeline_mem;
@@ -216,6 +218,7 @@ unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
 unsigned int get_num_sdma_queues(struct device_queue_manager *dqm);
+unsigned int get_num_xgmi_sdma_queues(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
index 33830b1a5a54..604570bea6bd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
@@ -175,6 +175,7 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 			queue_type__mes_map_queues__debug_interface_queue_vi;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
+	case KFD_QUEUE_TYPE_SDMA_XGMI:
 		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
 				engine_sel__mes_map_queues__sdma0_vi;
 		use_static = false; /* no static queues under SDMA */
@@ -221,6 +222,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 			engine_sel__mes_unmap_queues__compute;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
+	case KFD_QUEUE_TYPE_SDMA_XGMI:
 		packet->bitfields2.engine_sel =
 			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
 		break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
index bf20c6d32ef3..3cdb19826927 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
@@ -212,6 +212,7 @@ static int pm_map_queues_vi(struct packet_manager *pm, uint32_t *buffer,
 			queue_type__mes_map_queues__debug_interface_queue_vi;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
+	case KFD_QUEUE_TYPE_SDMA_XGMI:
 		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
 				engine_sel__mes_map_queues__sdma0_vi;
 		use_static = false; /* no static queues under SDMA */
@@ -258,6 +259,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
 			engine_sel__mes_unmap_queues__compute;
 		break;
 	case KFD_QUEUE_TYPE_SDMA:
+	case KFD_QUEUE_TYPE_SDMA_XGMI:
 		packet->bitfields2.engine_sel =
 			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
 		break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 045a229436a0..077c47fd4fee 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -48,7 +48,8 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
 
 	process_count = pm->dqm->processes_count;
 	queue_count = pm->dqm->queue_count;
-	compute_queue_count = queue_count - pm->dqm->sdma_queue_count;
+	compute_queue_count = queue_count - pm->dqm->sdma_queue_count -
+				pm->dqm->xgmi_sdma_queue_count;
 
 	/* check if there is over subscription
 	 * Note: the arbitration between the number of VMIDs and
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 10bd1abe1646..8f02d7817162 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -188,6 +188,7 @@ struct kfd_device_info {
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
 	unsigned int num_sdma_engines;
+	unsigned int num_xgmi_sdma_engines;
 	unsigned int num_sdma_queues_per_engine;
 };
 
@@ -329,7 +330,8 @@ enum kfd_queue_type  {
 	KFD_QUEUE_TYPE_COMPUTE,
 	KFD_QUEUE_TYPE_SDMA,
 	KFD_QUEUE_TYPE_HIQ,
-	KFD_QUEUE_TYPE_DIQ
+	KFD_QUEUE_TYPE_DIQ,
+	KFD_QUEUE_TYPE_SDMA_XGMI
 };
 
 enum kfd_queue_format {
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 f18d9cdf9aac..e652e25ede75 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -186,8 +186,13 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
-			pr_err("Over-subscription is not allowed for SDMA.\n");
+	case KFD_QUEUE_TYPE_SDMA_XGMI:
+		if ((type == KFD_QUEUE_TYPE_SDMA && dev->dqm->sdma_queue_count
+			>= get_num_sdma_queues(dev->dqm)) ||
+			(type == KFD_QUEUE_TYPE_SDMA_XGMI &&
+			dev->dqm->xgmi_sdma_queue_count
+			>= get_num_xgmi_sdma_queues(dev->dqm))) {
+			pr_debug("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
@@ -446,6 +451,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 			q = pqn->q;
 			switch (q->properties.type) {
 			case KFD_QUEUE_TYPE_SDMA:
+			case KFD_QUEUE_TYPE_SDMA_XGMI:
 				seq_printf(m, "  SDMA queue on device %x\n",
 					   q->device->id);
 				mqd_type = KFD_MQD_TYPE_SDMA;