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>

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;
 

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,
 };
 

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)
 {

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;

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;

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

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 {

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;

include/uapi/linux/kfd_ioctl.h

@@ -35,9 +35,10 @@ struct kfd_ioctl_get_version_args {
 };
 
 /* For kfd_ioctl_create_queue_args.queue_type. */
-#define KFD_IOC_QUEUE_TYPE_COMPUTE	0
-#define KFD_IOC_QUEUE_TYPE_SDMA		1
-#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL	2
+#define KFD_IOC_QUEUE_TYPE_COMPUTE		0x0
+#define KFD_IOC_QUEUE_TYPE_SDMA			0x1
+#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL		0x2
+#define KFD_IOC_QUEUE_TYPE_SDMA_XGMI		0x3
 
 #define KFD_MAX_QUEUE_PERCENTAGE	100
 #define KFD_MAX_QUEUE_PRIORITY		15