diff mbox series

[RFC,16/17] drm/amdkfd: CRIU implement gpu_id remapping

Message ID 20210501015752.888-17-Felix.Kuehling@amd.com (mailing list archive)
State New, archived
Headers show
Series CRIU support for ROCm | expand

Commit Message

Felix Kuehling May 1, 2021, 1:57 a.m. UTC 
From: David Yat Sin <david.yatsin@amd.com>

When doing a restore on a different node, the gpu_id's on the restore
node may be different. But the user space application will still refer
use the original gpu_id's in the ioctl calls. Adding code to create a
gpu id mapping so that kfd can determine actual gpu_id during the user
ioctl's.

Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Change-Id: I8f72afe847c9ef7b25a902b30516e9043f1b5834
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 245 +++++++++++++----------
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |   3 +
 drivers/gpu/drm/amd/amdkfd/kfd_process.c |  18 ++
 3 files changed, 157 insertions(+), 109 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ce511b246beb..8e92c68eb9c5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -294,13 +294,14 @@  static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 		return err;
 
 	pr_debug("Looking for gpu id 0x%x\n", args->gpu_id);
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev) {
+
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
 		pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
 		return -EINVAL;
 	}
-
-	mutex_lock(&p->mutex);
+	dev = pdd->dev;
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
@@ -491,7 +492,6 @@  static int kfd_ioctl_set_memory_policy(struct file *filep,
 					struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_set_memory_policy_args *args = data;
-	struct kfd_dev *dev;
 	int err = 0;
 	struct kfd_process_device *pdd;
 	enum cache_policy default_policy, alternate_policy;
@@ -506,13 +506,15 @@  static int kfd_ioctl_set_memory_policy(struct file *filep,
 		return -EINVAL;
 	}
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
 	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
+		err = -EINVAL;
+		goto out;
+	}
 
-	pdd = kfd_bind_process_to_device(dev, p);
+	pdd = kfd_bind_process_to_device(pdd->dev, p);
 	if (IS_ERR(pdd)) {
 		err = -ESRCH;
 		goto out;
@@ -525,7 +527,7 @@  static int kfd_ioctl_set_memory_policy(struct file *filep,
 		(args->alternate_policy == KFD_IOC_CACHE_POLICY_COHERENT)
 		   ? cache_policy_coherent : cache_policy_noncoherent;
 
-	if (!dev->dqm->ops.set_cache_memory_policy(dev->dqm,
+	if (!pdd->dev->dqm->ops.set_cache_memory_policy(pdd->dev->dqm,
 				&pdd->qpd,
 				default_policy,
 				alternate_policy,
@@ -543,17 +545,18 @@  static int kfd_ioctl_set_trap_handler(struct file *filep,
 					struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_set_trap_handler_args *args = data;
-	struct kfd_dev *dev;
 	int err = 0;
 	struct kfd_process_device *pdd;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
 	mutex_lock(&p->mutex);
 
-	pdd = kfd_bind_process_to_device(dev, p);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	pdd = kfd_bind_process_to_device(pdd->dev, p);
 	if (IS_ERR(pdd)) {
 		err = -ESRCH;
 		goto out;
@@ -577,16 +580,20 @@  static int kfd_ioctl_dbg_register(struct file *filep,
 	bool create_ok;
 	long status = 0;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		status = -EINVAL;
+		goto out_unlock_p;
+	}
+	dev = pdd->dev;
 
 	if (dev->device_info->asic_family == CHIP_CARRIZO) {
 		pr_debug("kfd_ioctl_dbg_register not supported on CZ\n");
-		return -EINVAL;
+		status = -EINVAL;
+		goto out_unlock_p;
 	}
 
-	mutex_lock(&p->mutex);
 	mutex_lock(kfd_get_dbgmgr_mutex());
 
 	/*
@@ -596,7 +603,7 @@  static int kfd_ioctl_dbg_register(struct file *filep,
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
 		status = PTR_ERR(pdd);
-		goto out;
+		goto out_unlock_dbg;
 	}
 
 	if (!dev->dbgmgr) {
@@ -614,8 +621,9 @@  static int kfd_ioctl_dbg_register(struct file *filep,
 		status = -EINVAL;
 	}
 
-out:
+out_unlock_dbg:
 	mutex_unlock(kfd_get_dbgmgr_mutex());
+out_unlock_p:
 	mutex_unlock(&p->mutex);
 
 	return status;
@@ -625,12 +633,18 @@  static int kfd_ioctl_dbg_unregister(struct file *filep,
 				struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_dbg_unregister_args *args = data;
+	struct kfd_process_device *pdd;
 	struct kfd_dev *dev;
 	long status;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev || !dev->dbgmgr)
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd || !pdd->dev->dbgmgr) {
+		mutex_unlock(&p->mutex);
 		return -EINVAL;
+	}
+	dev = pdd->dev;
+	mutex_unlock(&p->mutex);
 
 	if (dev->device_info->asic_family == CHIP_CARRIZO) {
 		pr_debug("kfd_ioctl_dbg_unregister not supported on CZ\n");
@@ -664,6 +678,7 @@  static int kfd_ioctl_dbg_address_watch(struct file *filep,
 {
 	struct kfd_ioctl_dbg_address_watch_args *args = data;
 	struct kfd_dev *dev;
+	struct kfd_process_device *pdd;
 	struct dbg_address_watch_info aw_info;
 	unsigned char *args_buff;
 	long status;
@@ -673,9 +688,15 @@  static int kfd_ioctl_dbg_address_watch(struct file *filep,
 
 	memset((void *) &aw_info, 0, sizeof(struct dbg_address_watch_info));
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
+		pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
 		return -EINVAL;
+	}
+	dev = pdd->dev;
+	mutex_unlock(&p->mutex);
 
 	if (dev->device_info->asic_family == CHIP_CARRIZO) {
 		pr_debug("kfd_ioctl_dbg_wave_control not supported on CZ\n");
@@ -764,6 +785,7 @@  static int kfd_ioctl_dbg_wave_control(struct file *filep,
 {
 	struct kfd_ioctl_dbg_wave_control_args *args = data;
 	struct kfd_dev *dev;
+	struct kfd_process_device *pdd;
 	struct dbg_wave_control_info wac_info;
 	unsigned char *args_buff;
 	uint32_t computed_buff_size;
@@ -781,9 +803,15 @@  static int kfd_ioctl_dbg_wave_control(struct file *filep,
 				sizeof(wac_info.dbgWave_msg.MemoryVA) +
 				sizeof(wac_info.trapId);
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
+		pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
 		return -EINVAL;
+	}
+	dev = pdd->dev;
+	mutex_unlock(&p->mutex);
 
 	if (dev->device_info->asic_family == CHIP_CARRIZO) {
 		pr_debug("kfd_ioctl_dbg_wave_control not supported on CZ\n");
@@ -847,16 +875,19 @@  static int kfd_ioctl_get_clock_counters(struct file *filep,
 				struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_get_clock_counters_args *args = data;
-	struct kfd_dev *dev;
+	struct kfd_process_device *pdd;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (dev)
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (pdd)
 		/* Reading GPU clock counter from KGD */
-		args->gpu_clock_counter = amdgpu_amdkfd_get_gpu_clock_counter(dev->kgd);
+		args->gpu_clock_counter = amdgpu_amdkfd_get_gpu_clock_counter(pdd->dev->kgd);
 	else
 		/* Node without GPU resource */
 		args->gpu_clock_counter = 0;
 
+	mutex_unlock(&p->mutex);
+
 	/* No access to rdtsc. Using raw monotonic time */
 	args->cpu_clock_counter = ktime_get_raw_ns();
 	args->system_clock_counter = ktime_get_boottime_ns();
@@ -1010,15 +1041,15 @@  static int kmap_event_page(struct kfd_process *p, uint64_t event_page_offset)
 		return -EINVAL;
 	}
 
-	kfd = kfd_device_by_id(GET_GPU_ID(event_page_offset));
-	if (!kfd) {
+	pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(event_page_offset));
+	if (!pdd) {
 		pr_err("Getting device by id failed in %s\n", __func__);
 		return -EINVAL;
 	}
+	kfd = pdd->dev;
 
 	pdd = kfd_bind_process_to_device(kfd, p);
 	if (IS_ERR(pdd)) {
-		mutex_unlock(&p->mutex);
 		return PTR_ERR(pdd);
 	}
 
@@ -1026,8 +1057,6 @@  static int kmap_event_page(struct kfd_process *p, uint64_t event_page_offset)
 			GET_IDR_HANDLE(event_page_offset));
 	if (!mem) {
 		pr_err("Can't find BO, offset is 0x%llx\n", event_page_offset);
-
-		mutex_unlock(&p->mutex);
 		return -EINVAL;
 	}
 
@@ -1119,11 +1148,13 @@  static int kfd_ioctl_set_scratch_backing_va(struct file *filep,
 	struct kfd_dev *dev;
 	long err;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
 	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		err = -EINVAL;
+		goto bind_process_to_device_fail;
+	}
+	dev = pdd->dev;
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
@@ -1151,15 +1182,20 @@  static int kfd_ioctl_get_tile_config(struct file *filep,
 		struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_get_tile_config_args *args = data;
-	struct kfd_dev *dev;
+	struct kfd_process_device *pdd;
 	struct tile_config config;
 	int err = 0;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
 		return -EINVAL;
+	}
+
+	amdgpu_amdkfd_get_tile_config(pdd->dev->kgd, &config);
 
-	amdgpu_amdkfd_get_tile_config(dev->kgd, &config);
+	mutex_unlock(&p->mutex);
 
 	args->gb_addr_config = config.gb_addr_config;
 	args->num_banks = config.num_banks;
@@ -1194,21 +1230,15 @@  static int kfd_ioctl_acquire_vm(struct file *filep, struct kfd_process *p,
 {
 	struct kfd_ioctl_acquire_vm_args *args = data;
 	struct kfd_process_device *pdd;
-	struct kfd_dev *dev;
 	struct file *drm_file;
 	int ret;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
 	drm_file = fget(args->drm_fd);
 	if (!drm_file)
 		return -EINVAL;
 
 	mutex_lock(&p->mutex);
-
-	pdd = kfd_get_process_device_data(dev, p);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
 	if (!pdd) {
 		ret = -EINVAL;
 		goto err_unlock;
@@ -1267,19 +1297,23 @@  static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	if (args->size == 0)
 		return -EINVAL;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
+	dev = pdd->dev;
 
 	if ((flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) &&
 		(flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) &&
 		!kfd_dev_is_large_bar(dev)) {
 		pr_err("Alloc host visible vram on small bar is not allowed\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto err_unlock;
 	}
 
-	mutex_lock(&p->mutex);
-
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
 		err = PTR_ERR(pdd);
@@ -1350,17 +1384,12 @@  static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 	struct kfd_ioctl_free_memory_of_gpu_args *args = data;
 	struct kfd_process_device *pdd;
 	void *mem;
-	struct kfd_dev *dev;
 	int ret;
 	uint64_t size = 0;
 
-	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
-	if (!dev)
-		return -EINVAL;
-
 	mutex_lock(&p->mutex);
 
-	pdd = kfd_get_process_device_data(dev, p);
+	pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(args->handle));
 	if (!pdd) {
 		pr_err("Process device data doesn't exist\n");
 		ret = -EINVAL;
@@ -1374,7 +1403,7 @@  static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 		goto err_unlock;
 	}
 
-	ret = amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->kgd,
+	ret = amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->kgd,
 				(struct kgd_mem *)mem, pdd->drm_priv, &size);
 
 	/* If freeing the buffer failed, leave the handle in place for
@@ -1397,15 +1426,11 @@  static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	struct kfd_ioctl_map_memory_to_gpu_args *args = data;
 	struct kfd_process_device *pdd, *peer_pdd;
 	void *mem;
-	struct kfd_dev *dev, *peer;
+	struct kfd_dev *dev;
 	long err = 0;
 	int i;
 	uint32_t *devices_arr = NULL;
 
-	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
-	if (!dev)
-		return -EINVAL;
-
 	if (!args->n_devices) {
 		pr_debug("Device IDs array empty\n");
 		return -EINVAL;
@@ -1429,6 +1454,12 @@  static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	}
 
 	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(args->handle));
+	if (!pdd) {
+		err = -EINVAL;
+		goto get_process_device_data_failed;
+	}
+	dev = pdd->dev;
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
@@ -1444,21 +1475,21 @@  static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	}
 
 	for (i = args->n_success; i < args->n_devices; i++) {
-		peer = kfd_device_by_id(devices_arr[i]);
-		if (!peer) {
+		peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
+		if (!peer_pdd) {
 			pr_debug("Getting device by id failed for 0x%x\n",
 				 devices_arr[i]);
 			err = -EINVAL;
 			goto get_mem_obj_from_handle_failed;
 		}
 
-		peer_pdd = kfd_bind_process_to_device(peer, p);
+		peer_pdd = kfd_bind_process_to_device(peer_pdd->dev, p);
 		if (IS_ERR(peer_pdd)) {
 			err = PTR_ERR(peer_pdd);
 			goto get_mem_obj_from_handle_failed;
 		}
 		err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-			peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+			peer_pdd->dev->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
 		if (err) {
 			pr_err("Failed to map to gpu %d/%d\n",
 			       i, args->n_devices);
@@ -1477,12 +1508,10 @@  static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 
 	/* Flush TLBs after waiting for the page table updates to complete */
 	for (i = 0; i < args->n_devices; i++) {
-		peer = kfd_device_by_id(devices_arr[i]);
-		if (WARN_ON_ONCE(!peer))
-			continue;
-		peer_pdd = kfd_get_process_device_data(peer, p);
+		peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
 		if (WARN_ON_ONCE(!peer_pdd))
 			continue;
+
 		kfd_flush_tlb(peer_pdd);
 	}
 
@@ -1490,6 +1519,7 @@  static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 
 	return err;
 
+get_process_device_data_failed:
 bind_process_to_device_failed:
 get_mem_obj_from_handle_failed:
 map_memory_to_gpu_failed:
@@ -1507,14 +1537,9 @@  static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 	struct kfd_ioctl_unmap_memory_from_gpu_args *args = data;
 	struct kfd_process_device *pdd, *peer_pdd;
 	void *mem;
-	struct kfd_dev *dev, *peer;
 	long err = 0;
 	uint32_t *devices_arr = NULL, i;
 
-	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
-	if (!dev)
-		return -EINVAL;
-
 	if (!args->n_devices) {
 		pr_debug("Device IDs array empty\n");
 		return -EINVAL;
@@ -1538,8 +1563,7 @@  static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 	}
 
 	mutex_lock(&p->mutex);
-
-	pdd = kfd_get_process_device_data(dev, p);
+	pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(args->handle));
 	if (!pdd) {
 		err = -EINVAL;
 		goto bind_process_to_device_failed;
@@ -1553,19 +1577,13 @@  static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 	}
 
 	for (i = args->n_success; i < args->n_devices; i++) {
-		peer = kfd_device_by_id(devices_arr[i]);
-		if (!peer) {
-			err = -EINVAL;
-			goto get_mem_obj_from_handle_failed;
-		}
-
-		peer_pdd = kfd_get_process_device_data(peer, p);
+		peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]);
 		if (!peer_pdd) {
-			err = -ENODEV;
+			err = -EINVAL;
 			goto get_mem_obj_from_handle_failed;
 		}
 		err = amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
-			peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+			peer_pdd->dev->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
 		if (err) {
 			pr_err("Failed to unmap from gpu %d/%d\n",
 			       i, args->n_devices);
@@ -1694,23 +1712,26 @@  static int kfd_ioctl_import_dmabuf(struct file *filep,
 	void *mem;
 	int r;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
+	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		r = -EINVAL;
+		goto err_unlock;
+	}
 
 	dmabuf = dma_buf_get(args->dmabuf_fd);
-	if (IS_ERR(dmabuf))
-		return PTR_ERR(dmabuf);
-
-	mutex_lock(&p->mutex);
+	if (IS_ERR(dmabuf)) {
+		r = PTR_ERR(dmabuf);
+		goto err_unlock;
+	}
 
-	pdd = kfd_bind_process_to_device(dev, p);
+	pdd = kfd_bind_process_to_device(pdd->dev, p);
 	if (IS_ERR(pdd)) {
 		r = PTR_ERR(pdd);
 		goto err_unlock;
 	}
 
-	r = amdgpu_amdkfd_gpuvm_import_dmabuf(dev->kgd, dmabuf,
+	r = amdgpu_amdkfd_gpuvm_import_dmabuf(pdd->dev->kgd, dmabuf,
 					      args->va_addr, pdd->drm_priv,
 					      (struct kgd_mem **)&mem, &size,
 					      NULL);
@@ -1744,13 +1765,19 @@  static int kfd_ioctl_smi_events(struct file *filep,
 				struct kfd_process *p, void *data)
 {
 	struct kfd_ioctl_smi_events_args *args = data;
-	struct kfd_dev *dev;
+	struct kfd_process_device *pdd;
 
-	dev = kfd_device_by_id(args->gpuid);
-	if (!dev)
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_process_device_data_by_id(p, args->gpuid);
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
 		return -EINVAL;
+	}
+
+	mutex_unlock(&p->mutex);
 
-	return kfd_smi_event_open(dev, &args->anon_fd);
+	return kfd_smi_event_open(pdd->dev, &args->anon_fd);
 }
 
 static int kfd_ioctl_set_xnack_mode(struct file *filep,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d3265860e78b..b2ea00e7309f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -930,6 +930,9 @@  int kfd_process_restore_queues(struct kfd_process *p);
 void kfd_suspend_all_processes(void);
 int kfd_resume_all_processes(void);
 
+struct kfd_process_device *kfd_process_device_data_by_id(struct kfd_process *process,
+				uint32_t gpu_id);
+
 int kfd_process_device_init_vm(struct kfd_process_device *pdd,
 			       struct file *drm_file);
 struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index bbf21395fb06..604b2b398be2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1424,6 +1424,7 @@  struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 	pdd->runtime_inuse = false;
 	pdd->vram_usage = 0;
 	pdd->sdma_past_activity_counter = 0;
+	pdd->user_gpu_id = dev->id;
 	atomic64_set(&pdd->evict_duration_counter, 0);
 	p->pdds[p->n_pdds++] = pdd;
 
@@ -1897,6 +1898,23 @@  void kfd_flush_tlb(struct kfd_process_device *pdd)
 	}
 }
 
+struct kfd_process_device *kfd_process_device_data_by_id(struct kfd_process *p, uint32_t gpu_id)
+{
+	int i;
+
+	if (gpu_id) {
+		for (i = 0; i < p->n_pdds; i++) {
+			struct kfd_process_device *pdd = p->pdds[i];
+
+			if (pdd->user_gpu_id == gpu_id)
+				return pdd;
+		}
+
+		WARN_ONCE(1, "Failed to find mapping for gpu = 0x%x\n",  gpu_id);
+	}
+	return NULL;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 int kfd_debugfs_mqds_by_process(struct seq_file *m, void *data)