1 files changed, 269 insertions, 131 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d97e330a5022..8a2c6fc438c0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -42,6 +42,7 @@ struct mm_struct;
 #include "kfd_device_queue_manager.h"
 #include "kfd_dbgmgr.h"
 #include "kfd_iommu.h"
+#include "kfd_svm.h"
 
 /*
  * List of struct kfd_process (field kfd_process).
@@ -108,8 +109,6 @@ static void kfd_sdma_activity_worker(struct work_struct *work)
 
 	workarea = container_of(work, struct kfd_sdma_activity_handler_workarea,
 				sdma_activity_work);
-	if (!workarea)
-		return;
 
 	pdd = workarea->pdd;
 	if (!pdd)
@@ -250,7 +249,7 @@ cleanup:
 }
 
 /**
- * @kfd_get_cu_occupancy() - Collect number of waves in-flight on this device
+ * @kfd_get_cu_occupancy - Collect number of waves in-flight on this device
  * by current process. Translates acquired wave count into number of compute units
  * that are occupied.
  *
@@ -417,6 +416,29 @@ static ssize_t kfd_procfs_stats_show(struct kobject *kobj,
 	return 0;
 }
 
+static ssize_t kfd_sysfs_counters_show(struct kobject *kobj,
+				       struct attribute *attr, char *buf)
+{
+	struct kfd_process_device *pdd;
+
+	if (!strcmp(attr->name, "faults")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_faults);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->faults));
+	}
+	if (!strcmp(attr->name, "page_in")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_page_in);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_in));
+	}
+	if (!strcmp(attr->name, "page_out")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_page_out);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_out));
+	}
+	return 0;
+}
+
 static struct attribute attr_queue_size = {
 	.name = "size",
 	.mode = KFD_SYSFS_FILE_MODE
@@ -452,13 +474,18 @@ static const struct sysfs_ops procfs_stats_ops = {
 	.show = kfd_procfs_stats_show,
 };
 
-static struct attribute *procfs_stats_attrs[] = {
-	NULL
-};
-
 static struct kobj_type procfs_stats_type = {
 	.sysfs_ops = &procfs_stats_ops,
-	.default_attrs = procfs_stats_attrs,
+	.release = kfd_procfs_kobj_release,
+};
+
+static const struct sysfs_ops sysfs_counters_ops = {
+	.show = kfd_sysfs_counters_show,
+};
+
+static struct kobj_type sysfs_counters_type = {
+	.sysfs_ops = &sysfs_counters_ops,
+	.release = kfd_procfs_kobj_release,
 };
 
 int kfd_procfs_add_queue(struct queue *q)
@@ -485,34 +512,31 @@ int kfd_procfs_add_queue(struct queue *q)
 	return 0;
 }
 
-static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr,
+static void kfd_sysfs_create_file(struct kobject *kobj, struct attribute *attr,
 				 char *name)
 {
-	int ret = 0;
+	int ret;
 
-	if (!p || !attr || !name)
-		return -EINVAL;
+	if (!kobj || !attr || !name)
+		return;
 
 	attr->name = name;
 	attr->mode = KFD_SYSFS_FILE_MODE;
 	sysfs_attr_init(attr);
 
-	ret = sysfs_create_file(p->kobj, attr);
-
-	return ret;
+	ret = sysfs_create_file(kobj, attr);
+	if (ret)
+		pr_warn("Create sysfs %s/%s failed %d", kobj->name, name, ret);
 }
 
-static int kfd_procfs_add_sysfs_stats(struct kfd_process *p)
+static void kfd_procfs_add_sysfs_stats(struct kfd_process *p)
 {
-	int ret = 0;
+	int ret;
 	int i;
 	char stats_dir_filename[MAX_SYSFS_FILENAME_LEN];
 
-	if (!p)
-		return -EINVAL;
-
-	if (!p->kobj)
-		return -EFAULT;
+	if (!p || !p->kobj)
+		return;
 
 	/*
 	 * Create sysfs files for each GPU:
@@ -522,63 +546,87 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p)
 	 */
 	for (i = 0; i < p->n_pdds; i++) {
 		struct kfd_process_device *pdd = p->pdds[i];
-		struct kobject *kobj_stats;
 
 		snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN,
 				"stats_%u", pdd->dev->id);
-		kobj_stats = kfd_alloc_struct(kobj_stats);
-		if (!kobj_stats)
-			return -ENOMEM;
+		pdd->kobj_stats = kfd_alloc_struct(pdd->kobj_stats);
+		if (!pdd->kobj_stats)
+			return;
 
-		ret = kobject_init_and_add(kobj_stats,
-						&procfs_stats_type,
-						p->kobj,
-						stats_dir_filename);
+		ret = kobject_init_and_add(pdd->kobj_stats,
+					   &procfs_stats_type,
+					   p->kobj,
+					   stats_dir_filename);
 
 		if (ret) {
 			pr_warn("Creating KFD proc/stats_%s folder failed",
-					stats_dir_filename);
-			kobject_put(kobj_stats);
-			goto err;
+				stats_dir_filename);
+			kobject_put(pdd->kobj_stats);
+			pdd->kobj_stats = NULL;
+			return;
 		}
 
-		pdd->kobj_stats = kobj_stats;
-		pdd->attr_evict.name = "evicted_ms";
-		pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE;
-		sysfs_attr_init(&pdd->attr_evict);
-		ret = sysfs_create_file(kobj_stats, &pdd->attr_evict);
-		if (ret)
-			pr_warn("Creating eviction stats for gpuid %d failed",
-					(int)pdd->dev->id);
-
+		kfd_sysfs_create_file(pdd->kobj_stats, &pdd->attr_evict,
+				      "evicted_ms");
 		/* Add sysfs file to report compute unit occupancy */
-		if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) {
-			pdd->attr_cu_occupancy.name = "cu_occupancy";
-			pdd->attr_cu_occupancy.mode = KFD_SYSFS_FILE_MODE;
-			sysfs_attr_init(&pdd->attr_cu_occupancy);
-			ret = sysfs_create_file(kobj_stats,
-						&pdd->attr_cu_occupancy);
-			if (ret)
-				pr_warn("Creating %s failed for gpuid: %d",
-					pdd->attr_cu_occupancy.name,
-					(int)pdd->dev->id);
-		}
+		if (pdd->dev->kfd2kgd->get_cu_occupancy)
+			kfd_sysfs_create_file(pdd->kobj_stats,
+					      &pdd->attr_cu_occupancy,
+					      "cu_occupancy");
 	}
-err:
-	return ret;
 }
 
-
-static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
+static void kfd_procfs_add_sysfs_counters(struct kfd_process *p)
 {
 	int ret = 0;
 	int i;
+	char counters_dir_filename[MAX_SYSFS_FILENAME_LEN];
 
-	if (!p)
-		return -EINVAL;
+	if (!p || !p->kobj)
+		return;
 
-	if (!p->kobj)
-		return -EFAULT;
+	/*
+	 * Create sysfs files for each GPU which supports SVM
+	 * - proc/<pid>/counters_<gpuid>/
+	 * - proc/<pid>/counters_<gpuid>/faults
+	 * - proc/<pid>/counters_<gpuid>/page_in
+	 * - proc/<pid>/counters_<gpuid>/page_out
+	 */
+	for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) {
+		struct kfd_process_device *pdd = p->pdds[i];
+		struct kobject *kobj_counters;
+
+		snprintf(counters_dir_filename, MAX_SYSFS_FILENAME_LEN,
+			"counters_%u", pdd->dev->id);
+		kobj_counters = kfd_alloc_struct(kobj_counters);
+		if (!kobj_counters)
+			return;
+
+		ret = kobject_init_and_add(kobj_counters, &sysfs_counters_type,
+					   p->kobj, counters_dir_filename);
+		if (ret) {
+			pr_warn("Creating KFD proc/%s folder failed",
+				counters_dir_filename);
+			kobject_put(kobj_counters);
+			return;
+		}
+
+		pdd->kobj_counters = kobj_counters;
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_faults,
+				      "faults");
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_in,
+				      "page_in");
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_out,
+				      "page_out");
+	}
+}
+
+static void kfd_procfs_add_sysfs_files(struct kfd_process *p)
+{
+	int i;
+
+	if (!p || !p->kobj)
+		return;
 
 	/*
 	 * Create sysfs files for each GPU:
@@ -590,20 +638,14 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
 
 		snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u",
 			 pdd->dev->id);
-		ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename);
-		if (ret)
-			pr_warn("Creating vram usage for gpu id %d failed",
-				(int)pdd->dev->id);
+		kfd_sysfs_create_file(p->kobj, &pdd->attr_vram,
+				      pdd->vram_filename);
 
 		snprintf(pdd->sdma_filename, MAX_SYSFS_FILENAME_LEN, "sdma_%u",
 			 pdd->dev->id);
-		ret = kfd_sysfs_create_file(p, &pdd->attr_sdma, pdd->sdma_filename);
-		if (ret)
-			pr_warn("Creating sdma usage for gpu id %d failed",
-				(int)pdd->dev->id);
+		kfd_sysfs_create_file(p->kobj, &pdd->attr_sdma,
+					    pdd->sdma_filename);
 	}
-
-	return ret;
 }
 
 void kfd_procfs_del_queue(struct queue *q)
@@ -647,8 +689,9 @@ static void kfd_process_free_gpuvm(struct kgd_mem *mem,
 {
 	struct kfd_dev *dev = pdd->dev;
 
-	amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(dev->kgd, mem, pdd->vm);
-	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, mem, NULL);
+	amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(dev->kgd, mem, pdd->drm_priv);
+	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd, mem, pdd->drm_priv,
+					       NULL);
 }
 
 /* kfd_process_alloc_gpuvm - Allocate GPU VM for the KFD process
@@ -667,11 +710,11 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd,
 	int err;
 
 	err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(kdev->kgd, gpu_va, size,
-						 pdd->vm, &mem, NULL, flags);
+						 pdd->drm_priv, &mem, NULL, flags);
 	if (err)
 		goto err_alloc_mem;
 
-	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->vm);
+	err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv);
 	if (err)
 		goto err_map_mem;
 
@@ -712,7 +755,8 @@ sync_memory_failed:
 	return err;
 
 err_map_mem:
-	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(kdev->kgd, mem, NULL);
+	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(kdev->kgd, mem, pdd->drm_priv,
+					       NULL);
 err_alloc_mem:
 	*kptr = NULL;
 	return err;
@@ -798,28 +842,17 @@ struct kfd_process *kfd_create_process(struct file *filep)
 			goto out;
 		}
 
-		process->attr_pasid.name = "pasid";
-		process->attr_pasid.mode = KFD_SYSFS_FILE_MODE;
-		sysfs_attr_init(&process->attr_pasid);
-		ret = sysfs_create_file(process->kobj, &process->attr_pasid);
-		if (ret)
-			pr_warn("Creating pasid for pid %d failed",
-					(int)process->lead_thread->pid);
+		kfd_sysfs_create_file(process->kobj, &process->attr_pasid,
+				      "pasid");
 
 		process->kobj_queues = kobject_create_and_add("queues",
 							process->kobj);
 		if (!process->kobj_queues)
 			pr_warn("Creating KFD proc/queues folder failed");
 
-		ret = kfd_procfs_add_sysfs_stats(process);
-		if (ret)
-			pr_warn("Creating sysfs stats dir for pid %d failed",
-				(int)process->lead_thread->pid);
-
-		ret = kfd_procfs_add_sysfs_files(process);
-		if (ret)
-			pr_warn("Creating sysfs usage file for pid %d failed",
-				(int)process->lead_thread->pid);
+		kfd_procfs_add_sysfs_stats(process);
+		kfd_procfs_add_sysfs_files(process);
+		kfd_procfs_add_sysfs_counters(process);
 	}
 out:
 	if (!IS_ERR(process))
@@ -901,13 +934,14 @@ static void kfd_process_device_free_bos(struct kfd_process_device *pdd)
 		for (i = 0; i < p->n_pdds; i++) {
 			struct kfd_process_device *peer_pdd = p->pdds[i];
 
-			if (!peer_pdd->vm)
+			if (!peer_pdd->drm_priv)
 				continue;
 			amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
-				peer_pdd->dev->kgd, mem, peer_pdd->vm);
+				peer_pdd->dev->kgd, mem, peer_pdd->drm_priv);
 		}
 
-		amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->kgd, mem, NULL);
+		amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->kgd, mem,
+						       pdd->drm_priv, NULL);
 		kfd_process_device_remove_obj_handle(pdd, id);
 	}
 }
@@ -932,7 +966,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 
 		if (pdd->drm_file) {
 			amdgpu_amdkfd_gpuvm_release_process_vm(
-					pdd->dev->kgd, pdd->vm);
+					pdd->dev->kgd, pdd->drm_priv);
 			fput(pdd->drm_file);
 		}
 
@@ -961,6 +995,50 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 	p->n_pdds = 0;
 }
 
+static void kfd_process_remove_sysfs(struct kfd_process *p)
+{
+	struct kfd_process_device *pdd;
+	int i;
+
+	if (!p->kobj)
+		return;
+
+	sysfs_remove_file(p->kobj, &p->attr_pasid);
+	kobject_del(p->kobj_queues);
+	kobject_put(p->kobj_queues);
+	p->kobj_queues = NULL;
+
+	for (i = 0; i < p->n_pdds; i++) {
+		pdd = p->pdds[i];
+
+		sysfs_remove_file(p->kobj, &pdd->attr_vram);
+		sysfs_remove_file(p->kobj, &pdd->attr_sdma);
+
+		sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict);
+		if (pdd->dev->kfd2kgd->get_cu_occupancy)
+			sysfs_remove_file(pdd->kobj_stats,
+					  &pdd->attr_cu_occupancy);
+		kobject_del(pdd->kobj_stats);
+		kobject_put(pdd->kobj_stats);
+		pdd->kobj_stats = NULL;
+	}
+
+	for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) {
+		pdd = p->pdds[i];
+
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_faults);
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_in);
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_out);
+		kobject_del(pdd->kobj_counters);
+		kobject_put(pdd->kobj_counters);
+		pdd->kobj_counters = NULL;
+	}
+
+	kobject_del(p->kobj);
+	kobject_put(p->kobj);
+	p->kobj = NULL;
+}
+
 /* No process locking is needed in this function, because the process
  * is not findable any more. We must assume that no other thread is
  * using it any more, otherwise we couldn't safely free the process
@@ -970,36 +1048,11 @@ static void kfd_process_wq_release(struct work_struct *work)
 {
 	struct kfd_process *p = container_of(work, struct kfd_process,
 					     release_work);
-	int i;
-
-	/* Remove the procfs files */
-	if (p->kobj) {
-		sysfs_remove_file(p->kobj, &p->attr_pasid);
-		kobject_del(p->kobj_queues);
-		kobject_put(p->kobj_queues);
-		p->kobj_queues = NULL;
-
-		for (i = 0; i < p->n_pdds; i++) {
-			struct kfd_process_device *pdd = p->pdds[i];
-
-			sysfs_remove_file(p->kobj, &pdd->attr_vram);
-			sysfs_remove_file(p->kobj, &pdd->attr_sdma);
-			sysfs_remove_file(p->kobj, &pdd->attr_evict);
-			if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL)
-				sysfs_remove_file(p->kobj, &pdd->attr_cu_occupancy);
-			kobject_del(pdd->kobj_stats);
-			kobject_put(pdd->kobj_stats);
-			pdd->kobj_stats = NULL;
-		}
-
-		kobject_del(p->kobj);
-		kobject_put(p->kobj);
-		p->kobj = NULL;
-	}
-
+	kfd_process_remove_sysfs(p);
 	kfd_iommu_unbind_process(p);
 
 	kfd_process_free_outstanding_kfd_bos(p);
+	svm_range_list_fini(p);
 
 	kfd_process_destroy_pdds(p);
 	dma_fence_put(p->ef);
@@ -1058,6 +1111,7 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 
 	cancel_delayed_work_sync(&p->eviction_work);
 	cancel_delayed_work_sync(&p->restore_work);
+	cancel_delayed_work_sync(&p->svms.restore_work);
 
 	mutex_lock(&p->mutex);
 
@@ -1186,6 +1240,56 @@ void kfd_process_set_trap_handler(struct qcm_process_device *qpd,
 	}
 }
 
+bool kfd_process_xnack_mode(struct kfd_process *p, bool supported)
+{
+	int i;
+
+	/* On most GFXv9 GPUs, the retry mode in the SQ must match the
+	 * boot time retry setting. Mixing processes with different
+	 * XNACK/retry settings can hang the GPU.
+	 *
+	 * Different GPUs can have different noretry settings depending
+	 * on HW bugs or limitations. We need to find at least one
+	 * XNACK mode for this process that's compatible with all GPUs.
+	 * Fortunately GPUs with retry enabled (noretry=0) can run code
+	 * built for XNACK-off. On GFXv9 it may perform slower.
+	 *
+	 * Therefore applications built for XNACK-off can always be
+	 * supported and will be our fallback if any GPU does not
+	 * support retry.
+	 */
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_dev *dev = p->pdds[i]->dev;
+
+		/* Only consider GFXv9 and higher GPUs. Older GPUs don't
+		 * support the SVM APIs and don't need to be considered
+		 * for the XNACK mode selection.
+		 */
+		if (dev->device_info->asic_family < CHIP_VEGA10)
+			continue;
+		/* Aldebaran can always support XNACK because it can support
+		 * per-process XNACK mode selection. But let the dev->noretry
+		 * setting still influence the default XNACK mode.
+		 */
+		if (supported &&
+		    dev->device_info->asic_family == CHIP_ALDEBARAN)
+			continue;
+
+		/* GFXv10 and later GPUs do not support shader preemption
+		 * during page faults. This can lead to poor QoS for queue
+		 * management and memory-manager-related preemptions or
+		 * even deadlocks.
+		 */
+		if (dev->device_info->asic_family >= CHIP_NAVI10)
+			return false;
+
+		if (dev->noretry)
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * On return the kfd_process is fully operational and will be freed when the
  * mm is released
@@ -1224,6 +1328,13 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	if (err != 0)
 		goto err_init_apertures;
 
+	/* Check XNACK support after PDDs are created in kfd_init_apertures */
+	process->xnack_enabled = kfd_process_xnack_mode(process, false);
+
+	err = svm_range_list_init(process);
+	if (err)
+		goto err_init_svm_range_list;
+
 	/* alloc_notifier needs to find the process in the hash table */
 	hash_add_rcu(kfd_processes_table, &process->kfd_processes,
 			(uintptr_t)process->mm);
@@ -1246,6 +1357,8 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 
 err_register_notifier:
 	hash_del_rcu(&process->kfd_processes);
+	svm_range_list_fini(process);
+err_init_svm_range_list:
 	kfd_process_free_outstanding_kfd_bos(process);
 	kfd_process_destroy_pdds(process);
 err_init_apertures:
@@ -1375,7 +1488,7 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
 	if (!drm_file)
 		return -EINVAL;
 
-	if (pdd->vm)
+	if (pdd->drm_priv)
 		return -EBUSY;
 
 	p = pdd->process;
@@ -1383,13 +1496,12 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
 
 	ret = amdgpu_amdkfd_gpuvm_acquire_process_vm(
 		dev->kgd, drm_file, p->pasid,
-		&pdd->vm, &p->kgd_process_info, &p->ef);
+		&p->kgd_process_info, &p->ef);
 	if (ret) {
 		pr_err("Failed to create process VM object\n");
 		return ret;
 	}
-
-	amdgpu_vm_set_task_info(pdd->vm);
+	pdd->drm_priv = drm_file->private_data;
 
 	ret = kfd_process_device_reserve_ib_mem(pdd);
 	if (ret)
@@ -1405,7 +1517,7 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd,
 err_init_cwsr:
 err_reserve_ib_mem:
 	kfd_process_device_free_bos(pdd);
-	pdd->vm = NULL;
+	pdd->drm_priv = NULL;
 
 	return ret;
 }
@@ -1429,7 +1541,7 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (!pdd->vm)
+	if (!pdd->drm_priv)
 		return ERR_PTR(-ENODEV);
 
 	/*
@@ -1600,6 +1712,32 @@ int kfd_process_restore_queues(struct kfd_process *p)
 	return ret;
 }
 
+int kfd_process_gpuidx_from_gpuid(struct kfd_process *p, uint32_t gpu_id)
+{
+	int i;
+
+	for (i = 0; i < p->n_pdds; i++)
+		if (p->pdds[i] && gpu_id == p->pdds[i]->dev->id)
+			return i;
+	return -EINVAL;
+}
+
+int
+kfd_process_gpuid_from_kgd(struct kfd_process *p, struct amdgpu_device *adev,
+			   uint32_t *gpuid, uint32_t *gpuidx)
+{
+	struct kgd_dev *kgd = (struct kgd_dev *)adev;
+	int i;
+
+	for (i = 0; i < p->n_pdds; i++)
+		if (p->pdds[i] && p->pdds[i]->dev->kgd == kgd) {
+			*gpuid = p->pdds[i]->dev->id;
+			*gpuidx = i;
+			return 0;
+		}
+	return -EINVAL;
+}
+
 static void evict_process_worker(struct work_struct *work)
 {
 	int ret;
@@ -1748,7 +1886,7 @@ int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 			       KFD_CWSR_TBA_TMA_SIZE, vma->vm_page_prot);
 }
 
-void kfd_flush_tlb(struct kfd_process_device *pdd)
+void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type)
 {
 	struct kfd_dev *dev = pdd->dev;
 
@@ -1761,7 +1899,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd)
 							pdd->qpd.vmid);
 	} else {
 		amdgpu_amdkfd_flush_gpu_tlb_pasid(dev->kgd,
-						pdd->process->pasid);
+					pdd->process->pasid, type);
 	}
 }