drm/amdkfd: Make SDMA engine number an ASIC-dependent variable

On Raven there is only one SDMA engine instead of previously assumed two,
so we need to adapt our code to this new scenario.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -52,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -67,6 +68,7 @@ static const struct kfd_device_info carrizo_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 #endif
 
@@ -83,6 +85,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_device_info = {
@@ -97,6 +100,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_vf_device_info = {
@@ -111,6 +115,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_device_info = {
@@ -125,6 +130,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_vf_device_info = {
@@ -139,6 +145,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -154,6 +161,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris10_vf_device_info = {
@@ -168,6 +176,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris11_device_info = {
@@ -182,6 +191,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_device_info = {
@@ -196,6 +206,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_vf_device_info = {
@@ -210,6 +221,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -101,6 +101,17 @@ unsigned int get_pipes_per_mec(struct device_queue_manager *dqm)
 	return dqm->dev->shared_resources.num_pipe_per_mec;
 }
 
+static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines;
+}
+
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines
+			* KFD_SDMA_QUEUES_PER_ENGINE;
+}
+
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
@@ -855,7 +866,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	}
 
 	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	return 0;
 }
@@ -903,7 +914,7 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id)
 {
-	if (sdma_queue_id >= CIK_SDMA_QUEUES)
+	if (sdma_queue_id >= get_num_sdma_queues(dqm))
 		return;
 	dqm->sdma_bitmap |= (1 << sdma_queue_id);
 }
@@ -923,8 +934,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_queue_id = q->sdma_id / get_num_sdma_engines(dqm);
+	q->properties.sdma_engine_id = q->sdma_id % get_num_sdma_engines(dqm);
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
@@ -1011,7 +1022,7 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
@@ -1142,9 +1153,9 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		if (retval)
 			goto out_unlock;
 		q->properties.sdma_queue_id =
-			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id / get_num_sdma_engines(dqm);
 		q->properties.sdma_engine_id =
-			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id % get_num_sdma_engines(dqm);
 	}
 
 	retval = allocate_doorbell(qpd, q);
@@ -1791,8 +1802,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 		}
 	}
 
-	for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) {
-		for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) {
+	for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) {
+		for (queue = 0; queue < KFD_SDMA_QUEUES_PER_ENGINE; queue++) {
 			r = dqm->dev->kfd2kgd->hqd_sdma_dump(
 				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
 			if (r)

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

@@ -33,10 +33,7 @@
 
 #define KFD_UNMAP_LATENCY_MS			(4000)
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
-
-#define CIK_SDMA_QUEUES				(4)
-#define CIK_SDMA_QUEUES_PER_ENGINE		(2)
-#define CIK_SDMA_ENGINE_NUM			(2)
+#define KFD_SDMA_QUEUES_PER_ENGINE		(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;
@@ -214,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 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);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -203,6 +203,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	unsigned int num_sdma_engines;
 };
 
 struct kfd_mem_obj {

drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c

@@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >=
-			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
 			pr_err("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;