Merge tag 'amd-drm-next-5.18-2022-02-11-1' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.18-2022-02-11-1:

amdgpu:
- Clean up of power management code
- Enable freesync video mode by default
- Clean up of RAS code
- Improve VRAM access for debug using SDMA
- Coding style cleanups
- SR-IOV fixes
- More display FP reorg
- TLB flush fixes for Arcuturus, Vega20
- Misc display fixes
- Rework special register access methods for SR-IOV
- DP2 fixes
- DP tunneling fixes
- DSC fixes
- More IP discovery cleanups
- Misc RAS fixes
- Enable both SMU i2c buses where applicable
- s2idle improvements
- DPCS header cleanup
- Add new CAP firmware support for SR-IOV

amdkfd:
- Misc cleanups
- SVM fixes
- CRIU support
- Clean up MQD manager

UAPI:
- Add interface to amdgpu CTX ioctl to request a stable power state for profiling
  https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/207
- Add amdkfd support for CRIU
  https://github.com/checkpoint-restore/criu/pull/1709
- Remove old unused amdkfd debugger interface
  Was only implemented for Kaveri and was only ever used by an old HSA tool that was never open sourced

radeon:
- Fix error handling in radeon_driver_open_kms
- UVD suspend fix
- Misc fixes

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220211220706.5803-1-alexander.deucher@amd.com

27 files changed, 3213 insertions, 2425 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index c4f3aff11072..19cfbf9577b4 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -51,8 +51,6 @@ AMDKFD_FILES	:= $(AMDKFD_PATH)/kfd_module.o \
 		$(AMDKFD_PATH)/kfd_events.o \
 		$(AMDKFD_PATH)/cik_event_interrupt.o \
 		$(AMDKFD_PATH)/kfd_int_process_v9.o \
-		$(AMDKFD_PATH)/kfd_dbgdev.o \
-		$(AMDKFD_PATH)/kfd_dbgmgr.o \
 		$(AMDKFD_PATH)/kfd_smi_events.o \
 		$(AMDKFD_PATH)/kfd_crat.o
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index d60576ce10cd..5c8023cba196 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -110,7 +110,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 		struct kfd_vm_fault_info info;
 
 		kfd_smi_event_update_vmfault(dev, pasid);
-		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_dqm_evict_pasid(dev->dqm, pasid);
 
 		memset(&info, 0, sizeof(info));
 		amdgpu_amdkfd_gpuvm_get_vm_fault_info(dev->adev, &info);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 4bfc0c8ab764..54d997f304b5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -33,14 +33,16 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/ptrace.h>
 #include <linux/dma-buf.h>
+#include <linux/fdtable.h>
 #include <asm/processor.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
-#include "kfd_dbgmgr.h"
 #include "kfd_svm.h"
 #include "amdgpu_amdkfd.h"
 #include "kfd_smi_events.h"
+#include "amdgpu_dma_buf.h"
 
 static long kfd_ioctl(struct file *, unsigned int, unsigned long);
 static int kfd_open(struct inode *, struct file *);
@@ -292,14 +294,17 @@ 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) {
-		pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
-		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 err_pdd;
+	}
+	dev = pdd->dev;
+
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
 		err = -ESRCH;
@@ -310,7 +315,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 			p->pasid,
 			dev->id);
 
-	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id,
+	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL, NULL,
 			&doorbell_offset_in_process);
 	if (err != 0)
 		goto err_create_queue;
@@ -344,6 +349,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 err_create_queue:
 err_bind_process:
+err_pdd:
 	mutex_unlock(&p->mutex);
 	return err;
 }
@@ -490,7 +496,6 @@ 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;
@@ -505,13 +510,15 @@ 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 err_pdd;
+	}
 
-	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;
@@ -524,7 +531,7 @@ 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,
@@ -533,6 +540,7 @@ static int kfd_ioctl_set_memory_policy(struct file *filep,
 		err = -EINVAL;
 
 out:
+err_pdd:
 	mutex_unlock(&p->mutex);
 
 	return err;
@@ -542,17 +550,18 @@ 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 err_pdd;
+	}
+
+	pdd = kfd_bind_process_to_device(pdd->dev, p);
 	if (IS_ERR(pdd)) {
 		err = -ESRCH;
 		goto out;
@@ -561,6 +570,7 @@ static int kfd_ioctl_set_trap_handler(struct file *filep,
 	kfd_process_set_trap_handler(&pdd->qpd, args->tba_addr, args->tma_addr);
 
 out:
+err_pdd:
 	mutex_unlock(&p->mutex);
 
 	return err;
@@ -569,289 +579,40 @@ out:
 static int kfd_ioctl_dbg_register(struct file *filep,
 				struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_dbg_register_args *args = data;
-	struct kfd_dev *dev;
-	struct kfd_dbgmgr *dbgmgr_ptr;
-	struct kfd_process_device *pdd;
-	bool create_ok;
-	long status = 0;
-
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
-	if (dev->adev->asic_type == CHIP_CARRIZO) {
-		pr_debug("kfd_ioctl_dbg_register not supported on CZ\n");
-		return -EINVAL;
-	}
-
-	mutex_lock(&p->mutex);
-	mutex_lock(kfd_get_dbgmgr_mutex());
-
-	/*
-	 * make sure that we have pdd, if this the first queue created for
-	 * this process
-	 */
-	pdd = kfd_bind_process_to_device(dev, p);
-	if (IS_ERR(pdd)) {
-		status = PTR_ERR(pdd);
-		goto out;
-	}
-
-	if (!dev->dbgmgr) {
-		/* In case of a legal call, we have no dbgmgr yet */
-		create_ok = kfd_dbgmgr_create(&dbgmgr_ptr, dev);
-		if (create_ok) {
-			status = kfd_dbgmgr_register(dbgmgr_ptr, p);
-			if (status != 0)
-				kfd_dbgmgr_destroy(dbgmgr_ptr);
-			else
-				dev->dbgmgr = dbgmgr_ptr;
-		}
-	} else {
-		pr_debug("debugger already registered\n");
-		status = -EINVAL;
-	}
-
-out:
-	mutex_unlock(kfd_get_dbgmgr_mutex());
-	mutex_unlock(&p->mutex);
-
-	return status;
+	return -EPERM;
 }
 
 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_dev *dev;
-	long status;
-
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev || !dev->dbgmgr)
-		return -EINVAL;
-
-	if (dev->adev->asic_type == CHIP_CARRIZO) {
-		pr_debug("kfd_ioctl_dbg_unregister not supported on CZ\n");
-		return -EINVAL;
-	}
-
-	mutex_lock(kfd_get_dbgmgr_mutex());
-
-	status = kfd_dbgmgr_unregister(dev->dbgmgr, p);
-	if (!status) {
-		kfd_dbgmgr_destroy(dev->dbgmgr);
-		dev->dbgmgr = NULL;
-	}
-
-	mutex_unlock(kfd_get_dbgmgr_mutex());
-
-	return status;
+	return -EPERM;
 }
 
-/*
- * Parse and generate variable size data structure for address watch.
- * Total size of the buffer and # watch points is limited in order
- * to prevent kernel abuse. (no bearing to the much smaller HW limitation
- * which is enforced by dbgdev module)
- * please also note that the watch address itself are not "copied from user",
- * since it be set into the HW in user mode values.
- *
- */
 static int kfd_ioctl_dbg_address_watch(struct file *filep,
 					struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_dbg_address_watch_args *args = data;
-	struct kfd_dev *dev;
-	struct dbg_address_watch_info aw_info;
-	unsigned char *args_buff;
-	long status;
-	void __user *cmd_from_user;
-	uint64_t watch_mask_value = 0;
-	unsigned int args_idx = 0;
-
-	memset((void *) &aw_info, 0, sizeof(struct dbg_address_watch_info));
-
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
-	if (dev->adev->asic_type == CHIP_CARRIZO) {
-		pr_debug("kfd_ioctl_dbg_wave_control not supported on CZ\n");
-		return -EINVAL;
-	}
-
-	cmd_from_user = (void __user *) args->content_ptr;
-
-	/* Validate arguments */
-
-	if ((args->buf_size_in_bytes > MAX_ALLOWED_AW_BUFF_SIZE) ||
-		(args->buf_size_in_bytes <= sizeof(*args) + sizeof(int) * 2) ||
-		(cmd_from_user == NULL))
-		return -EINVAL;
-
-	/* this is the actual buffer to work with */
-	args_buff = memdup_user(cmd_from_user,
-				args->buf_size_in_bytes - sizeof(*args));
-	if (IS_ERR(args_buff))
-		return PTR_ERR(args_buff);
-
-	aw_info.process = p;
-
-	aw_info.num_watch_points = *((uint32_t *)(&args_buff[args_idx]));
-	args_idx += sizeof(aw_info.num_watch_points);
-
-	aw_info.watch_mode = (enum HSA_DBG_WATCH_MODE *) &args_buff[args_idx];
-	args_idx += sizeof(enum HSA_DBG_WATCH_MODE) * aw_info.num_watch_points;
-
-	/*
-	 * set watch address base pointer to point on the array base
-	 * within args_buff
-	 */
-	aw_info.watch_address = (uint64_t *) &args_buff[args_idx];
-
-	/* skip over the addresses buffer */
-	args_idx += sizeof(aw_info.watch_address) * aw_info.num_watch_points;
-
-	if (args_idx >= args->buf_size_in_bytes - sizeof(*args)) {
-		status = -EINVAL;
-		goto out;
-	}
-
-	watch_mask_value = (uint64_t) args_buff[args_idx];
-
-	if (watch_mask_value > 0) {
-		/*
-		 * There is an array of masks.
-		 * set watch mask base pointer to point on the array base
-		 * within args_buff
-		 */
-		aw_info.watch_mask = (uint64_t *) &args_buff[args_idx];
-
-		/* skip over the masks buffer */
-		args_idx += sizeof(aw_info.watch_mask) *
-				aw_info.num_watch_points;
-	} else {
-		/* just the NULL mask, set to NULL and skip over it */
-		aw_info.watch_mask = NULL;
-		args_idx += sizeof(aw_info.watch_mask);
-	}
-
-	if (args_idx >= args->buf_size_in_bytes - sizeof(args)) {
-		status = -EINVAL;
-		goto out;
-	}
-
-	/* Currently HSA Event is not supported for DBG */
-	aw_info.watch_event = NULL;
-
-	mutex_lock(kfd_get_dbgmgr_mutex());
-
-	status = kfd_dbgmgr_address_watch(dev->dbgmgr, &aw_info);
-
-	mutex_unlock(kfd_get_dbgmgr_mutex());
-
-out:
-	kfree(args_buff);
-
-	return status;
+	return -EPERM;
 }
 
 /* Parse and generate fixed size data structure for wave control */
 static int kfd_ioctl_dbg_wave_control(struct file *filep,
 					struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_dbg_wave_control_args *args = data;
-	struct kfd_dev *dev;
-	struct dbg_wave_control_info wac_info;
-	unsigned char *args_buff;
-	uint32_t computed_buff_size;
-	long status;
-	void __user *cmd_from_user;
-	unsigned int args_idx = 0;
-
-	memset((void *) &wac_info, 0, sizeof(struct dbg_wave_control_info));
-
-	/* we use compact form, independent of the packing attribute value */
-	computed_buff_size = sizeof(*args) +
-				sizeof(wac_info.mode) +
-				sizeof(wac_info.operand) +
-				sizeof(wac_info.dbgWave_msg.DbgWaveMsg) +
-				sizeof(wac_info.dbgWave_msg.MemoryVA) +
-				sizeof(wac_info.trapId);
-
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
-	if (dev->adev->asic_type == CHIP_CARRIZO) {
-		pr_debug("kfd_ioctl_dbg_wave_control not supported on CZ\n");
-		return -EINVAL;
-	}
-
-	/* input size must match the computed "compact" size */
-	if (args->buf_size_in_bytes != computed_buff_size) {
-		pr_debug("size mismatch, computed : actual %u : %u\n",
-				args->buf_size_in_bytes, computed_buff_size);
-		return -EINVAL;
-	}
-
-	cmd_from_user = (void __user *) args->content_ptr;
-
-	if (cmd_from_user == NULL)
-		return -EINVAL;
-
-	/* copy the entire buffer from user */
-
-	args_buff = memdup_user(cmd_from_user,
-				args->buf_size_in_bytes - sizeof(*args));
-	if (IS_ERR(args_buff))
-		return PTR_ERR(args_buff);
-
-	/* move ptr to the start of the "pay-load" area */
-	wac_info.process = p;
-
-	wac_info.operand = *((enum HSA_DBG_WAVEOP *)(&args_buff[args_idx]));
-	args_idx += sizeof(wac_info.operand);
-
-	wac_info.mode = *((enum HSA_DBG_WAVEMODE *)(&args_buff[args_idx]));
-	args_idx += sizeof(wac_info.mode);
-
-	wac_info.trapId = *((uint32_t *)(&args_buff[args_idx]));
-	args_idx += sizeof(wac_info.trapId);
-
-	wac_info.dbgWave_msg.DbgWaveMsg.WaveMsgInfoGen2.Value =
-					*((uint32_t *)(&args_buff[args_idx]));
-	wac_info.dbgWave_msg.MemoryVA = NULL;
-
-	mutex_lock(kfd_get_dbgmgr_mutex());
-
-	pr_debug("Calling dbg manager process %p, operand %u, mode %u, trapId %u, message %u\n",
-			wac_info.process, wac_info.operand,
-			wac_info.mode, wac_info.trapId,
-			wac_info.dbgWave_msg.DbgWaveMsg.WaveMsgInfoGen2.Value);
-
-	status = kfd_dbgmgr_wave_control(dev->dbgmgr, &wac_info);
-
-	pr_debug("Returned status of dbg manager is %ld\n", status);
-
-	mutex_unlock(kfd_get_dbgmgr_mutex());
-
-	kfree(args_buff);
-
-	return status;
+	return -EPERM;
 }
 
 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);
+	mutex_unlock(&p->mutex);
+	if (pdd)
 		/* Reading GPU clock counter from KGD */
-		args->gpu_clock_counter = amdgpu_amdkfd_get_gpu_clock_counter(dev->adev);
+		args->gpu_clock_counter = amdgpu_amdkfd_get_gpu_clock_counter(pdd->dev->adev);
 	else
 		/* Node without GPU resource */
 		args->gpu_clock_counter = 0;
@@ -1007,57 +768,11 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 	 * through the event_page_offset field.
 	 */
 	if (args->event_page_offset) {
-		struct kfd_dev *kfd;
-		struct kfd_process_device *pdd;
-		void *mem, *kern_addr;
-		uint64_t size;
-
-		kfd = kfd_device_by_id(GET_GPU_ID(args->event_page_offset));
-		if (!kfd) {
-			pr_err("Getting device by id failed in %s\n", __func__);
-			return -EINVAL;
-		}
-
 		mutex_lock(&p->mutex);
-
-		if (p->signal_page) {
-			pr_err("Event page is already set\n");
-			err = -EINVAL;
-			goto out_unlock;
-		}
-
-		pdd = kfd_bind_process_to_device(kfd, p);
-		if (IS_ERR(pdd)) {
-			err = PTR_ERR(pdd);
-			goto out_unlock;
-		}
-
-		mem = kfd_process_device_translate_handle(pdd,
-				GET_IDR_HANDLE(args->event_page_offset));
-		if (!mem) {
-			pr_err("Can't find BO, offset is 0x%llx\n",
-			       args->event_page_offset);
-			err = -EINVAL;
-			goto out_unlock;
-		}
-
-		err = amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(kfd->adev,
-						mem, &kern_addr, &size);
-		if (err) {
-			pr_err("Failed to map event page to kernel\n");
-			goto out_unlock;
-		}
-
-		err = kfd_event_page_set(p, kern_addr, size);
-		if (err) {
-			pr_err("Failed to set event page\n");
-			amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(kfd->adev, mem);
-			goto out_unlock;
-		}
-
-		p->signal_handle = args->event_page_offset;
-
+		err = kfd_kmap_event_page(p, args->event_page_offset);
 		mutex_unlock(&p->mutex);
+		if (err)
+			return err;
 	}
 
 	err = kfd_event_create(filp, p, args->event_type,
@@ -1066,10 +781,7 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 				&args->event_page_offset,
 				&args->event_slot_index);
 
-	return err;
-
-out_unlock:
-	mutex_unlock(&p->mutex);
+	pr_debug("Created event (id:0x%08x) (%s)\n", args->event_id, __func__);
 	return err;
 }
 
@@ -1118,11 +830,13 @@ 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 err_pdd;
+	}
+	dev = pdd->dev;
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
@@ -1142,6 +856,7 @@ static int kfd_ioctl_set_scratch_backing_va(struct file *filep,
 	return 0;
 
 bind_process_to_device_fail:
+err_pdd:
 	mutex_unlock(&p->mutex);
 	return err;
 }
@@ -1150,15 +865,17 @@ 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);
+	mutex_unlock(&p->mutex);
+	if (!pdd)
 		return -EINVAL;
 
-	amdgpu_amdkfd_get_tile_config(dev->adev, &config);
+	amdgpu_amdkfd_get_tile_config(pdd->dev->adev, &config);
 
 	args->gb_addr_config = config.gb_addr_config;
 	args->num_banks = config.num_banks;
@@ -1193,40 +910,37 @@ 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;
+		goto err_pdd;
 	}
 
 	if (pdd->drm_file) {
 		ret = pdd->drm_file == drm_file ? 0 : -EBUSY;
-		goto err_unlock;
+		goto err_drm_file;
 	}
 
 	ret = kfd_process_device_init_vm(pdd, drm_file);
 	if (ret)
 		goto err_unlock;
+
 	/* On success, the PDD keeps the drm_file reference */
 	mutex_unlock(&p->mutex);
 
 	return 0;
 
 err_unlock:
+err_pdd:
+err_drm_file:
 	mutex_unlock(&p->mutex);
 	fput(drm_file);
 	return ret;
@@ -1283,19 +997,23 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	}
 	mutex_unlock(&p->svms.lock);
 #endif
-	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_pdd;
+	}
+
+	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_large_bar;
 	}
 
-	mutex_lock(&p->mutex);
-
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
 		err = PTR_ERR(pdd);
@@ -1323,7 +1041,7 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		dev->adev, args->va_addr, args->size,
 		pdd->drm_priv, (struct kgd_mem **) &mem, &offset,
-		flags);
+		flags, false);
 
 	if (err)
 		goto err_unlock;
@@ -1356,6 +1074,8 @@ err_free:
 	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->adev, (struct kgd_mem *)mem,
 					       pdd->drm_priv, NULL);
 err_unlock:
+err_pdd:
+err_large_bar:
 	mutex_unlock(&p->mutex);
 	return err;
 }
@@ -1366,14 +1086,9 @@ 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);
 	/*
 	 * Safeguard to prevent user space from freeing signal BO.
@@ -1385,11 +1100,11 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 		goto err_unlock;
 	}
 
-	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;
-		goto err_unlock;
+		goto err_pdd;
 	}
 
 	mem = kfd_process_device_translate_handle(
@@ -1399,7 +1114,7 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 		goto err_unlock;
 	}
 
-	ret = amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->adev,
+	ret = amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->adev,
 				(struct kgd_mem *)mem, pdd->drm_priv, &size);
 
 	/* If freeing the buffer failed, leave the handle in place for
@@ -1412,26 +1127,30 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
 	WRITE_ONCE(pdd->vram_usage, pdd->vram_usage - size);
 
 err_unlock:
+err_pdd:
 	mutex_unlock(&p->mutex);
 	return ret;
 }
 
+static bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) {
+	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
+	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) &&
+	        dev->adev->sdma.instance[0].fw_version >= 18) ||
+	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
+}
+
 static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 					struct kfd_process *p, void *data)
 {
 	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;
 	bool table_freed = false;
 
-	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;
@@ -1455,6 +1174,12 @@ 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)) {
@@ -1470,21 +1195,22 @@ 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->adev, (struct kgd_mem *)mem,
+			peer_pdd->dev->adev, (struct kgd_mem *)mem,
 			peer_pdd->drm_priv, &table_freed);
 		if (err) {
 			pr_err("Failed to map to gpu %d/%d\n",
@@ -1503,12 +1229,9 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
 	}
 
 	/* Flush TLBs after waiting for the page table updates to complete */
-	if (table_freed) {
+	if (table_freed || !kfd_flush_tlb_after_unmap(dev)) {
 		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, TLB_FLUSH_LEGACY);
@@ -1518,6 +1241,7 @@ 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:
@@ -1535,14 +1259,9 @@ 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;
@@ -1566,8 +1285,7 @@ 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;
@@ -1581,19 +1299,13 @@ 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->adev, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+			peer_pdd->dev->adev, (struct kgd_mem *)mem, peer_pdd->drm_priv);
 		if (err) {
 			pr_err("Failed to unmap from gpu %d/%d\n",
 			       i, args->n_devices);
@@ -1603,8 +1315,8 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
 	}
 	mutex_unlock(&p->mutex);
 
-	if (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2)) {
-		err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev,
+	if (kfd_flush_tlb_after_unmap(pdd->dev)) {
+		err = amdgpu_amdkfd_gpuvm_sync_memory(pdd->dev->adev,
 				(struct kgd_mem *) mem, true);
 		if (err) {
 			pr_debug("Sync memory failed, wait interrupted by user signal\n");
@@ -1613,10 +1325,7 @@ static int kfd_ioctl_unmap_memory_from_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, TLB_FLUSH_HEAVYWEIGHT);
@@ -1736,29 +1445,29 @@ static int kfd_ioctl_import_dmabuf(struct file *filep,
 	struct kfd_ioctl_import_dmabuf_args *args = data;
 	struct kfd_process_device *pdd;
 	struct dma_buf *dmabuf;
-	struct kfd_dev *dev;
 	int idr_handle;
 	uint64_t size;
 	void *mem;
 	int r;
 
-	dev = kfd_device_by_id(args->gpu_id);
-	if (!dev)
-		return -EINVAL;
-
 	dmabuf = dma_buf_get(args->dmabuf_fd);
 	if (IS_ERR(dmabuf))
 		return PTR_ERR(dmabuf);
 
 	mutex_lock(&p->mutex);
+	pdd = kfd_process_device_data_by_id(p, args->gpu_id);
+	if (!pdd) {
+		r = -EINVAL;
+		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->adev, dmabuf,
+	r = amdgpu_amdkfd_gpuvm_import_dmabuf(pdd->dev->adev, dmabuf,
 					      args->va_addr, pdd->drm_priv,
 					      (struct kgd_mem **)&mem, &size,
 					      NULL);
@@ -1779,7 +1488,7 @@ static int kfd_ioctl_import_dmabuf(struct file *filep,
 	return 0;
 
 err_free:
-	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->adev, (struct kgd_mem *)mem,
+	amdgpu_amdkfd_gpuvm_free_memory_of_gpu(pdd->dev->adev, (struct kgd_mem *)mem,
 					       pdd->drm_priv, NULL);
 err_unlock:
 	mutex_unlock(&p->mutex);
@@ -1792,13 +1501,16 @@ 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);
+	mutex_unlock(&p->mutex);
+	if (!pdd)
 		return -EINVAL;
 
-	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,
@@ -1840,13 +1552,9 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 	if (!args->start_addr || !args->size)
 		return -EINVAL;
 
-	mutex_lock(&p->mutex);
-
 	r = svm_ioctl(p, args->op, args->start_addr, args->size, args->nattr,
 		      args->attrs);
 
-	mutex_unlock(&p->mutex);
-
 	return r;
 }
 #else
@@ -1856,6 +1564,1024 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
 }
 #endif
 
+static int criu_checkpoint_process(struct kfd_process *p,
+			     uint8_t __user *user_priv_data,
+			     uint64_t *priv_offset)
+{
+	struct kfd_criu_process_priv_data process_priv;
+	int ret;
+
+	memset(&process_priv, 0, sizeof(process_priv));
+
+	process_priv.version = KFD_CRIU_PRIV_VERSION;
+	/* For CR, we don't consider negative xnack mode which is used for
+	 * querying without changing it, here 0 simply means disabled and 1
+	 * means enabled so retry for finding a valid PTE.
+	 */
+	process_priv.xnack_mode = p->xnack_enabled ? 1 : 0;
+
+	ret = copy_to_user(user_priv_data + *priv_offset,
+				&process_priv, sizeof(process_priv));
+
+	if (ret) {
+		pr_err("Failed to copy process information to user\n");
+		ret = -EFAULT;
+	}
+
+	*priv_offset += sizeof(process_priv);
+	return ret;
+}
+
+static int criu_checkpoint_devices(struct kfd_process *p,
+			     uint32_t num_devices,
+			     uint8_t __user *user_addr,
+			     uint8_t __user *user_priv_data,
+			     uint64_t *priv_offset)
+{
+	struct kfd_criu_device_priv_data *device_priv = NULL;
+	struct kfd_criu_device_bucket *device_buckets = NULL;
+	int ret = 0, i;
+
+	device_buckets = kvzalloc(num_devices * sizeof(*device_buckets), GFP_KERNEL);
+	if (!device_buckets) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	device_priv = kvzalloc(num_devices * sizeof(*device_priv), GFP_KERNEL);
+	if (!device_priv) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	for (i = 0; i < num_devices; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+
+		device_buckets[i].user_gpu_id = pdd->user_gpu_id;
+		device_buckets[i].actual_gpu_id = pdd->dev->id;
+
+		/*
+		 * priv_data does not contain useful information for now and is reserved for
+		 * future use, so we do not set its contents.
+		 */
+	}
+
+	ret = copy_to_user(user_addr, device_buckets, num_devices * sizeof(*device_buckets));
+	if (ret) {
+		pr_err("Failed to copy device information to user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	ret = copy_to_user(user_priv_data + *priv_offset,
+			   device_priv,
+			   num_devices * sizeof(*device_priv));
+	if (ret) {
+		pr_err("Failed to copy device information to user\n");
+		ret = -EFAULT;
+	}
+	*priv_offset += num_devices * sizeof(*device_priv);
+
+exit:
+	kvfree(device_buckets);
+	kvfree(device_priv);
+	return ret;
+}
+
+static uint32_t get_process_num_bos(struct kfd_process *p)
+{
+	uint32_t num_of_bos = 0;
+	int i;
+
+	/* Run over all PDDs of the process */
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+		void *mem;
+		int id;
+
+		idr_for_each_entry(&pdd->alloc_idr, mem, id) {
+			struct kgd_mem *kgd_mem = (struct kgd_mem *)mem;
+
+			if ((uint64_t)kgd_mem->va > pdd->gpuvm_base)
+				num_of_bos++;
+		}
+	}
+	return num_of_bos;
+}
+
+static int criu_get_prime_handle(struct drm_gem_object *gobj, int flags,
+				      u32 *shared_fd)
+{
+	struct dma_buf *dmabuf;
+	int ret;
+
+	dmabuf = amdgpu_gem_prime_export(gobj, flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		pr_err("dmabuf export failed for the BO\n");
+		return ret;
+	}
+
+	ret = dma_buf_fd(dmabuf, flags);
+	if (ret < 0) {
+		pr_err("dmabuf create fd failed, ret:%d\n", ret);
+		goto out_free_dmabuf;
+	}
+
+	*shared_fd = ret;
+	return 0;
+
+out_free_dmabuf:
+	dma_buf_put(dmabuf);
+	return ret;
+}
+
+static int criu_checkpoint_bos(struct kfd_process *p,
+			       uint32_t num_bos,
+			       uint8_t __user *user_bos,
+			       uint8_t __user *user_priv_data,
+			       uint64_t *priv_offset)
+{
+	struct kfd_criu_bo_bucket *bo_buckets;
+	struct kfd_criu_bo_priv_data *bo_privs;
+	int ret = 0, pdd_index, bo_index = 0, id;
+	void *mem;
+
+	bo_buckets = kvzalloc(num_bos * sizeof(*bo_buckets), GFP_KERNEL);
+	if (!bo_buckets)
+		return -ENOMEM;
+
+	bo_privs = kvzalloc(num_bos * sizeof(*bo_privs), GFP_KERNEL);
+	if (!bo_privs) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	for (pdd_index = 0; pdd_index < p->n_pdds; pdd_index++) {
+		struct kfd_process_device *pdd = p->pdds[pdd_index];
+		struct amdgpu_bo *dumper_bo;
+		struct kgd_mem *kgd_mem;
+
+		idr_for_each_entry(&pdd->alloc_idr, mem, id) {
+			struct kfd_criu_bo_bucket *bo_bucket;
+			struct kfd_criu_bo_priv_data *bo_priv;
+			int i, dev_idx = 0;
+
+			if (!mem) {
+				ret = -ENOMEM;
+				goto exit;
+			}
+
+			kgd_mem = (struct kgd_mem *)mem;
+			dumper_bo = kgd_mem->bo;
+
+			if ((uint64_t)kgd_mem->va <= pdd->gpuvm_base)
+				continue;
+
+			bo_bucket = &bo_buckets[bo_index];
+			bo_priv = &bo_privs[bo_index];
+
+			bo_bucket->gpu_id = pdd->user_gpu_id;
+			bo_bucket->addr = (uint64_t)kgd_mem->va;
+			bo_bucket->size = amdgpu_bo_size(dumper_bo);
+			bo_bucket->alloc_flags = (uint32_t)kgd_mem->alloc_flags;
+			bo_priv->idr_handle = id;
+
+			if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
+				ret = amdgpu_ttm_tt_get_userptr(&dumper_bo->tbo,
+								&bo_priv->user_addr);
+				if (ret) {
+					pr_err("Failed to obtain user address for user-pointer bo\n");
+					goto exit;
+				}
+			}
+			if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
+				ret = criu_get_prime_handle(&dumper_bo->tbo.base,
+						bo_bucket->alloc_flags &
+						KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE ? DRM_RDWR : 0,
+						&bo_bucket->dmabuf_fd);
+				if (ret)
+					goto exit;
+			}
+			if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL)
+				bo_bucket->offset = KFD_MMAP_TYPE_DOORBELL |
+					KFD_MMAP_GPU_ID(pdd->dev->id);
+			else if (bo_bucket->alloc_flags &
+				KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)
+				bo_bucket->offset = KFD_MMAP_TYPE_MMIO |
+					KFD_MMAP_GPU_ID(pdd->dev->id);
+			else
+				bo_bucket->offset = amdgpu_bo_mmap_offset(dumper_bo);
+
+			for (i = 0; i < p->n_pdds; i++) {
+				if (amdgpu_amdkfd_bo_mapped_to_dev(p->pdds[i]->dev->adev, kgd_mem))
+					bo_priv->mapped_gpuids[dev_idx++] = p->pdds[i]->user_gpu_id;
+			}
+
+			pr_debug("bo_size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n"
+					"gpu_id = 0x%x alloc_flags = 0x%x idr_handle = 0x%x",
+					bo_bucket->size,
+					bo_bucket->addr,
+					bo_bucket->offset,
+					bo_bucket->gpu_id,
+					bo_bucket->alloc_flags,
+					bo_priv->idr_handle);
+			bo_index++;
+		}
+	}
+
+	ret = copy_to_user(user_bos, bo_buckets, num_bos * sizeof(*bo_buckets));
+	if (ret) {
+		pr_err("Failed to copy BO information to user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	ret = copy_to_user(user_priv_data + *priv_offset, bo_privs, num_bos * sizeof(*bo_privs));
+	if (ret) {
+		pr_err("Failed to copy BO priv information to user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	*priv_offset += num_bos * sizeof(*bo_privs);
+
+exit:
+	while (ret && bo_index--) {
+		if (bo_buckets[bo_index].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)
+			close_fd(bo_buckets[bo_index].dmabuf_fd);
+	}
+
+	kvfree(bo_buckets);
+	kvfree(bo_privs);
+	return ret;
+}
+
+static int criu_get_process_object_info(struct kfd_process *p,
+					uint32_t *num_devices,
+					uint32_t *num_bos,
+					uint32_t *num_objects,
+					uint64_t *objs_priv_size)
+{
+	uint64_t queues_priv_data_size, svm_priv_data_size, priv_size;
+	uint32_t num_queues, num_events, num_svm_ranges;
+	int ret;
+
+	*num_devices = p->n_pdds;
+	*num_bos = get_process_num_bos(p);
+
+	ret = kfd_process_get_queue_info(p, &num_queues, &queues_priv_data_size);
+	if (ret)
+		return ret;
+
+	num_events = kfd_get_num_events(p);
+
+	ret = svm_range_get_info(p, &num_svm_ranges, &svm_priv_data_size);
+	if (ret)
+		return ret;
+
+	*num_objects = num_queues + num_events + num_svm_ranges;
+
+	if (objs_priv_size) {
+		priv_size = sizeof(struct kfd_criu_process_priv_data);
+		priv_size += *num_devices * sizeof(struct kfd_criu_device_priv_data);
+		priv_size += *num_bos * sizeof(struct kfd_criu_bo_priv_data);
+		priv_size += queues_priv_data_size;
+		priv_size += num_events * sizeof(struct kfd_criu_event_priv_data);
+		priv_size += svm_priv_data_size;
+		*objs_priv_size = priv_size;
+	}
+	return 0;
+}
+
+static int criu_checkpoint(struct file *filep,
+			   struct kfd_process *p,
+			   struct kfd_ioctl_criu_args *args)
+{
+	int ret;
+	uint32_t num_devices, num_bos, num_objects;
+	uint64_t priv_size, priv_offset = 0;
+
+	if (!args->devices || !args->bos || !args->priv_data)
+		return -EINVAL;
+
+	mutex_lock(&p->mutex);
+
+	if (!p->n_pdds) {
+		pr_err("No pdd for given process\n");
+		ret = -ENODEV;
+		goto exit_unlock;
+	}
+
+	/* Confirm all process queues are evicted */
+	if (!p->queues_paused) {
+		pr_err("Cannot dump process when queues are not in evicted state\n");
+		/* CRIU plugin did not call op PROCESS_INFO before checkpointing */
+		ret = -EINVAL;
+		goto exit_unlock;
+	}
+
+	ret = criu_get_process_object_info(p, &num_devices, &num_bos, &num_objects, &priv_size);
+	if (ret)
+		goto exit_unlock;
+
+	if (num_devices != args->num_devices ||
+	    num_bos != args->num_bos ||
+	    num_objects != args->num_objects ||
+	    priv_size != args->priv_data_size) {
+
+		ret = -EINVAL;
+		goto exit_unlock;
+	}
+
+	/* each function will store private data inside priv_data and adjust priv_offset */
+	ret = criu_checkpoint_process(p, (uint8_t __user *)args->priv_data, &priv_offset);
+	if (ret)
+		goto exit_unlock;
+
+	ret = criu_checkpoint_devices(p, num_devices, (uint8_t __user *)args->devices,
+				(uint8_t __user *)args->priv_data, &priv_offset);
+	if (ret)
+		goto exit_unlock;
+
+	ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos,
+			    (uint8_t __user *)args->priv_data, &priv_offset);
+	if (ret)
+		goto exit_unlock;
+
+	if (num_objects) {
+		ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data,
+						 &priv_offset);
+		if (ret)
+			goto close_bo_fds;
+
+		ret = kfd_criu_checkpoint_events(p, (uint8_t __user *)args->priv_data,
+						 &priv_offset);
+		if (ret)
+			goto close_bo_fds;
+
+		ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset);
+		if (ret)
+			goto close_bo_fds;
+	}
+
+close_bo_fds:
+	if (ret) {
+		/* If IOCTL returns err, user assumes all FDs opened in criu_dump_bos are closed */
+		uint32_t i;
+		struct kfd_criu_bo_bucket *bo_buckets = (struct kfd_criu_bo_bucket *) args->bos;
+
+		for (i = 0; i < num_bos; i++) {
+			if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)
+				close_fd(bo_buckets[i].dmabuf_fd);
+		}
+	}
+
+exit_unlock:
+	mutex_unlock(&p->mutex);
+	if (ret)
+		pr_err("Failed to dump CRIU ret:%d\n", ret);
+	else
+		pr_debug("CRIU dump ret:%d\n", ret);
+
+	return ret;
+}
+
+static int criu_restore_process(struct kfd_process *p,
+				struct kfd_ioctl_criu_args *args,
+				uint64_t *priv_offset,
+				uint64_t max_priv_data_size)
+{
+	int ret = 0;
+	struct kfd_criu_process_priv_data process_priv;
+
+	if (*priv_offset + sizeof(process_priv) > max_priv_data_size)
+		return -EINVAL;
+
+	ret = copy_from_user(&process_priv,
+				(void __user *)(args->priv_data + *priv_offset),
+				sizeof(process_priv));
+	if (ret) {
+		pr_err("Failed to copy process private information from user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+	*priv_offset += sizeof(process_priv);
+
+	if (process_priv.version != KFD_CRIU_PRIV_VERSION) {
+		pr_err("Invalid CRIU API version (checkpointed:%d current:%d)\n",
+			process_priv.version, KFD_CRIU_PRIV_VERSION);
+		return -EINVAL;
+	}
+
+	pr_debug("Setting XNACK mode\n");
+	if (process_priv.xnack_mode && !kfd_process_xnack_mode(p, true)) {
+		pr_err("xnack mode cannot be set\n");
+		ret = -EPERM;
+		goto exit;
+	} else {
+		pr_debug("set xnack mode: %d\n", process_priv.xnack_mode);
+		p->xnack_enabled = process_priv.xnack_mode;
+	}
+
+exit:
+	return ret;
+}
+
+static int criu_restore_devices(struct kfd_process *p,
+				struct kfd_ioctl_criu_args *args,
+				uint64_t *priv_offset,
+				uint64_t max_priv_data_size)
+{
+	struct kfd_criu_device_bucket *device_buckets;
+	struct kfd_criu_device_priv_data *device_privs;
+	int ret = 0;
+	uint32_t i;
+
+	if (args->num_devices != p->n_pdds)
+		return -EINVAL;
+
+	if (*priv_offset + (args->num_devices * sizeof(*device_privs)) > max_priv_data_size)
+		return -EINVAL;
+
+	device_buckets = kmalloc_array(args->num_devices, sizeof(*device_buckets), GFP_KERNEL);
+	if (!device_buckets)
+		return -ENOMEM;
+
+	ret = copy_from_user(device_buckets, (void __user *)args->devices,
+				args->num_devices * sizeof(*device_buckets));
+	if (ret) {
+		pr_err("Failed to copy devices buckets from user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	for (i = 0; i < args->num_devices; i++) {
+		struct kfd_dev *dev;
+		struct kfd_process_device *pdd;
+		struct file *drm_file;
+
+		/* device private data is not currently used */
+
+		if (!device_buckets[i].user_gpu_id) {
+			pr_err("Invalid user gpu_id\n");
+			ret = -EINVAL;
+			goto exit;
+		}
+
+		dev = kfd_device_by_id(device_buckets[i].actual_gpu_id);
+		if (!dev) {
+			pr_err("Failed to find device with gpu_id = %x\n",
+				device_buckets[i].actual_gpu_id);
+			ret = -EINVAL;
+			goto exit;
+		}
+
+		pdd = kfd_get_process_device_data(dev, p);
+		if (!pdd) {
+			pr_err("Failed to get pdd for gpu_id = %x\n",
+					device_buckets[i].actual_gpu_id);
+			ret = -EINVAL;
+			goto exit;
+		}
+		pdd->user_gpu_id = device_buckets[i].user_gpu_id;
+
+		drm_file = fget(device_buckets[i].drm_fd);
+		if (!drm_file) {
+			pr_err("Invalid render node file descriptor sent from plugin (%d)\n",
+				device_buckets[i].drm_fd);
+			ret = -EINVAL;
+			goto exit;
+		}
+
+		if (pdd->drm_file) {
+			ret = -EINVAL;
+			goto exit;
+		}
+
+		/* create the vm using render nodes for kfd pdd */
+		if (kfd_process_device_init_vm(pdd, drm_file)) {
+			pr_err("could not init vm for given pdd\n");
+			/* On success, the PDD keeps the drm_file reference */
+			fput(drm_file);
+			ret = -EINVAL;
+			goto exit;
+		}
+		/*
+		 * pdd now already has the vm bound to render node so below api won't create a new
+		 * exclusive kfd mapping but use existing one with renderDXXX but is still needed
+		 * for iommu v2 binding  and runtime pm.
+		 */
+		pdd = kfd_bind_process_to_device(dev, p);
+		if (IS_ERR(pdd)) {
+			ret = PTR_ERR(pdd);
+			goto exit;
+		}
+	}
+
+	/*
+	 * We are not copying device private data from user as we are not using the data for now,
+	 * but we still adjust for its private data.
+	 */
+	*priv_offset += args->num_devices * sizeof(*device_privs);
+
+exit:
+	kfree(device_buckets);
+	return ret;
+}
+
+static int criu_restore_bos(struct kfd_process *p,
+			    struct kfd_ioctl_criu_args *args,
+			    uint64_t *priv_offset,
+			    uint64_t max_priv_data_size)
+{
+	struct kfd_criu_bo_bucket *bo_buckets;
+	struct kfd_criu_bo_priv_data *bo_privs;
+	const bool criu_resume = true;
+	bool flush_tlbs = false;
+	int ret = 0, j = 0;
+	uint32_t i = 0;
+
+	if (*priv_offset + (args->num_bos * sizeof(*bo_privs)) > max_priv_data_size)
+		return -EINVAL;
+
+	/* Prevent MMU notifications until stage-4 IOCTL (CRIU_RESUME) is received */
+	amdgpu_amdkfd_block_mmu_notifications(p->kgd_process_info);
+
+	bo_buckets = kvmalloc_array(args->num_bos, sizeof(*bo_buckets), GFP_KERNEL);
+	if (!bo_buckets)
+		return -ENOMEM;
+
+	ret = copy_from_user(bo_buckets, (void __user *)args->bos,
+			     args->num_bos * sizeof(*bo_buckets));
+	if (ret) {
+		pr_err("Failed to copy BOs information from user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	bo_privs = kvmalloc_array(args->num_bos, sizeof(*bo_privs), GFP_KERNEL);
+	if (!bo_privs) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	ret = copy_from_user(bo_privs, (void __user *)args->priv_data + *priv_offset,
+			     args->num_bos * sizeof(*bo_privs));
+	if (ret) {
+		pr_err("Failed to copy BOs information from user\n");
+		ret = -EFAULT;
+		goto exit;
+	}
+	*priv_offset += args->num_bos * sizeof(*bo_privs);
+
+	/* Create and map new BOs */
+	for (; i < args->num_bos; i++) {
+		struct kfd_criu_bo_bucket *bo_bucket;
+		struct kfd_criu_bo_priv_data *bo_priv;
+		struct kfd_dev *dev;
+		struct kfd_process_device *pdd;
+		struct kgd_mem *kgd_mem;
+		void *mem;
+		u64 offset;
+		int idr_handle;
+
+		bo_bucket = &bo_buckets[i];
+		bo_priv = &bo_privs[i];
+
+		pr_debug("kfd restore ioctl - bo_bucket[%d]:\n", i);
+		pr_debug("size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n"
+			"gpu_id = 0x%x alloc_flags = 0x%x\n"
+			"idr_handle = 0x%x\n",
+			bo_bucket->size,
+			bo_bucket->addr,
+			bo_bucket->offset,
+			bo_bucket->gpu_id,
+			bo_bucket->alloc_flags,
+			bo_priv->idr_handle);
+
+		pdd = kfd_process_device_data_by_id(p, bo_bucket->gpu_id);
+		if (!pdd) {
+			pr_err("Failed to get pdd\n");
+			ret = -ENODEV;
+			goto exit;
+		}
+		dev = pdd->dev;
+
+		if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) {
+			pr_debug("restore ioctl: KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL\n");
+			if (bo_bucket->size != kfd_doorbell_process_slice(dev)) {
+				ret = -EINVAL;
+				goto exit;
+			}
+			offset = kfd_get_process_doorbells(pdd);
+		} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
+			/* MMIO BOs need remapped bus address */
+			pr_debug("restore ioctl :KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP\n");
+			if (bo_bucket->size != PAGE_SIZE) {
+				pr_err("Invalid page size\n");
+				ret = -EINVAL;
+				goto exit;
+			}
+			offset = dev->adev->rmmio_remap.bus_addr;
+			if (!offset) {
+				pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n");
+				ret = -ENOMEM;
+				goto exit;
+			}
+		} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_USERPTR) {
+			offset = bo_priv->user_addr;
+		}
+		/* Create the BO */
+		ret = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(dev->adev,
+						bo_bucket->addr,
+						bo_bucket->size,
+						pdd->drm_priv,
+						(struct kgd_mem **) &mem,
+						&offset,
+						bo_bucket->alloc_flags,
+						criu_resume);
+		if (ret) {
+			pr_err("Could not create the BO\n");
+			ret = -ENOMEM;
+			goto exit;
+		}
+		pr_debug("New BO created: size = 0x%llx, bo_addr = 0x%llx bo_offset = 0x%llx\n",
+			bo_bucket->size, bo_bucket->addr, offset);
+
+		/* Restore previuos IDR handle */
+		pr_debug("Restoring old IDR handle for the BO");
+		idr_handle = idr_alloc(&pdd->alloc_idr, mem,
+				       bo_priv->idr_handle,
+				       bo_priv->idr_handle + 1, GFP_KERNEL);
+
+		if (idr_handle < 0) {
+			pr_err("Could not allocate idr\n");
+			amdgpu_amdkfd_gpuvm_free_memory_of_gpu(dev->adev,
+						(struct kgd_mem *)mem,
+						pdd->drm_priv, NULL);
+			ret = -ENOMEM;
+			goto exit;
+		}
+
+		if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL)
+			bo_bucket->restored_offset = KFD_MMAP_TYPE_DOORBELL |
+				KFD_MMAP_GPU_ID(pdd->dev->id);
+		if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
+			bo_bucket->restored_offset = KFD_MMAP_TYPE_MMIO |
+				KFD_MMAP_GPU_ID(pdd->dev->id);
+		} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) {
+			bo_bucket->restored_offset = offset;
+			pr_debug("updating offset for GTT\n");
+		} else if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
+			bo_bucket->restored_offset = offset;
+			/* Update the VRAM usage count */
+			WRITE_ONCE(pdd->vram_usage, pdd->vram_usage + bo_bucket->size);
+			pr_debug("updating offset for VRAM\n");
+		}
+
+		/* now map these BOs to GPU/s */
+		for (j = 0; j < p->n_pdds; j++) {
+			struct kfd_dev *peer;
+			struct kfd_process_device *peer_pdd;
+			bool table_freed = false;
+
+			if (!bo_priv->mapped_gpuids[j])
+				break;
+
+			peer_pdd = kfd_process_device_data_by_id(p, bo_priv->mapped_gpuids[j]);
+			if (!peer_pdd) {
+				ret = -EINVAL;
+				goto exit;
+			}
+			peer = peer_pdd->dev;
+
+			peer_pdd = kfd_bind_process_to_device(peer, p);
+			if (IS_ERR(peer_pdd)) {
+				ret = PTR_ERR(peer_pdd);
+				goto exit;
+			}
+			pr_debug("map mem in restore ioctl -> 0x%llx\n",
+				 ((struct kgd_mem *)mem)->va);
+			ret = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(peer->adev,
+				(struct kgd_mem *)mem, peer_pdd->drm_priv, &table_freed);
+			if (ret) {
+				pr_err("Failed to map to gpu %d/%d\n", j, p->n_pdds);
+				goto exit;
+			}
+			if (table_freed)
+				flush_tlbs = true;
+		}
+
+		ret = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev,
+						      (struct kgd_mem *) mem, true);
+		if (ret) {
+			pr_debug("Sync memory failed, wait interrupted by user signal\n");
+			goto exit;
+		}
+
+		pr_debug("map memory was successful for the BO\n");
+		/* create the dmabuf object and export the bo */
+		kgd_mem = (struct kgd_mem *)mem;
+		if (bo_bucket->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
+			ret = criu_get_prime_handle(&kgd_mem->bo->tbo.base,
+						    DRM_RDWR,
+						    &bo_bucket->dmabuf_fd);
+			if (ret)
+				goto exit;
+		}
+	} /* done */
+
+	if (flush_tlbs) {
+		/* Flush TLBs after waiting for the page table updates to complete */
+		for (j = 0; j < p->n_pdds; j++) {
+			struct kfd_dev *peer;
+			struct kfd_process_device *pdd = p->pdds[j];
+			struct kfd_process_device *peer_pdd;
+
+			peer = kfd_device_by_id(pdd->dev->id);
+			if (WARN_ON_ONCE(!peer))
+				continue;
+			peer_pdd = kfd_get_process_device_data(peer, p);
+			if (WARN_ON_ONCE(!peer_pdd))
+				continue;
+			kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+		}
+	}
+
+	/* Copy only the buckets back so user can read bo_buckets[N].restored_offset */
+	ret = copy_to_user((void __user *)args->bos,
+				bo_buckets,
+				(args->num_bos * sizeof(*bo_buckets)));
+	if (ret)
+		ret = -EFAULT;
+
+exit:
+	while (ret && i--) {
+		if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)
+			close_fd(bo_buckets[i].dmabuf_fd);
+	}
+	kvfree(bo_buckets);
+	kvfree(bo_privs);
+	return ret;
+}
+
+static int criu_restore_objects(struct file *filep,
+				struct kfd_process *p,
+				struct kfd_ioctl_criu_args *args,
+				uint64_t *priv_offset,
+				uint64_t max_priv_data_size)
+{
+	int ret = 0;
+	uint32_t i;
+
+	BUILD_BUG_ON(offsetof(struct kfd_criu_queue_priv_data, object_type));
+	BUILD_BUG_ON(offsetof(struct kfd_criu_event_priv_data, object_type));
+	BUILD_BUG_ON(offsetof(struct kfd_criu_svm_range_priv_data, object_type));
+
+	for (i = 0; i < args->num_objects; i++) {
+		uint32_t object_type;
+
+		if (*priv_offset + sizeof(object_type) > max_priv_data_size) {
+			pr_err("Invalid private data size\n");
+			return -EINVAL;
+		}
+
+		ret = get_user(object_type, (uint32_t __user *)(args->priv_data + *priv_offset));
+		if (ret) {
+			pr_err("Failed to copy private information from user\n");
+			goto exit;
+		}
+
+		switch (object_type) {
+		case KFD_CRIU_OBJECT_TYPE_QUEUE:
+			ret = kfd_criu_restore_queue(p, (uint8_t __user *)args->priv_data,
+						     priv_offset, max_priv_data_size);
+			if (ret)
+				goto exit;
+			break;
+		case KFD_CRIU_OBJECT_TYPE_EVENT:
+			ret = kfd_criu_restore_event(filep, p, (uint8_t __user *)args->priv_data,
+						     priv_offset, max_priv_data_size);
+			if (ret)
+				goto exit;
+			break;
+		case KFD_CRIU_OBJECT_TYPE_SVM_RANGE:
+			ret = kfd_criu_restore_svm(p, (uint8_t __user *)args->priv_data,
+						     priv_offset, max_priv_data_size);
+			if (ret)
+				goto exit;
+			break;
+		default:
+			pr_err("Invalid object type:%u at index:%d\n", object_type, i);
+			ret = -EINVAL;
+			goto exit;
+		}
+	}
+exit:
+	return ret;
+}
+
+static int criu_restore(struct file *filep,
+			struct kfd_process *p,
+			struct kfd_ioctl_criu_args *args)
+{
+	uint64_t priv_offset = 0;
+	int ret = 0;
+
+	pr_debug("CRIU restore (num_devices:%u num_bos:%u num_objects:%u priv_data_size:%llu)\n",
+		 args->num_devices, args->num_bos, args->num_objects, args->priv_data_size);
+
+	if (!args->bos || !args->devices || !args->priv_data || !args->priv_data_size ||
+	    !args->num_devices || !args->num_bos)
+		return -EINVAL;
+
+	mutex_lock(&p->mutex);
+
+	/*
+	 * Set the process to evicted state to avoid running any new queues before all the memory
+	 * mappings are ready.
+	 */
+	ret = kfd_process_evict_queues(p);
+	if (ret)
+		goto exit_unlock;
+
+	/* Each function will adjust priv_offset based on how many bytes they consumed */
+	ret = criu_restore_process(p, args, &priv_offset, args->priv_data_size);
+	if (ret)
+		goto exit_unlock;
+
+	ret = criu_restore_devices(p, args, &priv_offset, args->priv_data_size);
+	if (ret)
+		goto exit_unlock;
+
+	ret = criu_restore_bos(p, args, &priv_offset, args->priv_data_size);
+	if (ret)
+		goto exit_unlock;
+
+	ret = criu_restore_objects(filep, p, args, &priv_offset, args->priv_data_size);
+	if (ret)
+		goto exit_unlock;
+
+	if (priv_offset != args->priv_data_size) {
+		pr_err("Invalid private data size\n");
+		ret = -EINVAL;
+	}
+
+exit_unlock:
+	mutex_unlock(&p->mutex);
+	if (ret)
+		pr_err("Failed to restore CRIU ret:%d\n", ret);
+	else
+		pr_debug("CRIU restore successful\n");
+
+	return ret;
+}
+
+static int criu_unpause(struct file *filep,
+			struct kfd_process *p,
+			struct kfd_ioctl_criu_args *args)
+{
+	int ret;
+
+	mutex_lock(&p->mutex);
+
+	if (!p->queues_paused) {
+		mutex_unlock(&p->mutex);
+		return -EINVAL;
+	}
+
+	ret = kfd_process_restore_queues(p);
+	if (ret)
+		pr_err("Failed to unpause queues ret:%d\n", ret);
+	else
+		p->queues_paused = false;
+
+	mutex_unlock(&p->mutex);
+
+	return ret;
+}
+
+static int criu_resume(struct file *filep,
+			struct kfd_process *p,
+			struct kfd_ioctl_criu_args *args)
+{
+	struct kfd_process *target = NULL;
+	struct pid *pid = NULL;
+	int ret = 0;
+
+	pr_debug("Inside %s, target pid for criu restore: %d\n", __func__,
+		 args->pid);
+
+	pid = find_get_pid(args->pid);
+	if (!pid) {
+		pr_err("Cannot find pid info for %i\n", args->pid);
+		return -ESRCH;
+	}
+
+	pr_debug("calling kfd_lookup_process_by_pid\n");
+	target = kfd_lookup_process_by_pid(pid);
+
+	put_pid(pid);
+
+	if (!target) {
+		pr_debug("Cannot find process info for %i\n", args->pid);
+		return -ESRCH;
+	}
+
+	mutex_lock(&target->mutex);
+	ret = kfd_criu_resume_svm(target);
+	if (ret) {
+		pr_err("kfd_criu_resume_svm failed for %i\n", args->pid);
+		goto exit;
+	}
+
+	ret =  amdgpu_amdkfd_criu_resume(target->kgd_process_info);
+	if (ret)
+		pr_err("amdgpu_amdkfd_criu_resume failed for %i\n", args->pid);
+
+exit:
+	mutex_unlock(&target->mutex);
+
+	kfd_unref_process(target);
+	return ret;
+}
+
+static int criu_process_info(struct file *filep,
+				struct kfd_process *p,
+				struct kfd_ioctl_criu_args *args)
+{
+	int ret = 0;
+
+	mutex_lock(&p->mutex);
+
+	if (!p->n_pdds) {
+		pr_err("No pdd for given process\n");
+		ret = -ENODEV;
+		goto err_unlock;
+	}
+
+	ret = kfd_process_evict_queues(p);
+	if (ret)
+		goto err_unlock;
+
+	p->queues_paused = true;
+
+	args->pid = task_pid_nr_ns(p->lead_thread,
+					task_active_pid_ns(p->lead_thread));
+
+	ret = criu_get_process_object_info(p, &args->num_devices, &args->num_bos,
+					   &args->num_objects, &args->priv_data_size);
+	if (ret)
+		goto err_unlock;
+
+	dev_dbg(kfd_device, "Num of devices:%u bos:%u objects:%u priv_data_size:%lld\n",
+				args->num_devices, args->num_bos, args->num_objects,
+				args->priv_data_size);
+
+err_unlock:
+	if (ret) {
+		kfd_process_restore_queues(p);
+		p->queues_paused = false;
+	}
+	mutex_unlock(&p->mutex);
+	return ret;
+}
+
+static int kfd_ioctl_criu(struct file *filep, struct kfd_process *p, void *data)
+{
+	struct kfd_ioctl_criu_args *args = data;
+	int ret;
+
+	dev_dbg(kfd_device, "CRIU operation: %d\n", args->op);
+	switch (args->op) {
+	case KFD_CRIU_OP_PROCESS_INFO:
+		ret = criu_process_info(filep, p, args);
+		break;
+	case KFD_CRIU_OP_CHECKPOINT:
+		ret = criu_checkpoint(filep, p, args);
+		break;
+	case KFD_CRIU_OP_UNPAUSE:
+		ret = criu_unpause(filep, p, args);
+		break;
+	case KFD_CRIU_OP_RESTORE:
+		ret = criu_restore(filep, p, args);
+		break;
+	case KFD_CRIU_OP_RESUME:
+		ret = criu_resume(filep, p, args);
+		break;
+	default:
+		dev_dbg(kfd_device, "Unsupported CRIU operation:%d\n", args->op);
+		ret = -EINVAL;
+		break;
+	}
+
+	if (ret)
+		dev_dbg(kfd_device, "CRIU operation:%d err:%d\n", args->op, ret);
+
+	return ret;
+}
+
 #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
 	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \
 			    .cmd_drv = 0, .name = #ioctl}
@@ -1898,16 +2624,16 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_WAIT_EVENTS,
 			kfd_ioctl_wait_events, 0),
 
-	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_REGISTER,
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_REGISTER_DEPRECATED,
 			kfd_ioctl_dbg_register, 0),
 
-	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_UNREGISTER,
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_UNREGISTER_DEPRECATED,
 			kfd_ioctl_dbg_unregister, 0),
 
-	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_ADDRESS_WATCH,
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_ADDRESS_WATCH_DEPRECATED,
 			kfd_ioctl_dbg_address_watch, 0),
 
-	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_WAVE_CONTROL,
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_WAVE_CONTROL_DEPRECATED,
 			kfd_ioctl_dbg_wave_control, 0),
 
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_SCRATCH_BACKING_VA,
@@ -1959,6 +2685,10 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_XNACK_MODE,
 			kfd_ioctl_set_xnack_mode, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_CRIU_OP,
+			kfd_ioctl_criu, KFD_IOC_FLAG_CHECKPOINT_RESTORE),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
@@ -1973,6 +2703,7 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	char *kdata = NULL;
 	unsigned int usize, asize;
 	int retcode = -EINVAL;
+	bool ptrace_attached = false;
 
 	if (nr >= AMDKFD_CORE_IOCTL_COUNT)
 		goto err_i1;
@@ -1998,7 +2729,15 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	 * processes need to create their own KFD device context.
 	 */
 	process = filep->private_data;
-	if (process->lead_thread != current->group_leader) {
+
+	rcu_read_lock();
+	if ((ioctl->flags & KFD_IOC_FLAG_CHECKPOINT_RESTORE) &&
+	    ptrace_parent(process->lead_thread) == current)
+		ptrace_attached = true;
+	rcu_read_unlock();
+
+	if (process->lead_thread != current->group_leader
+	    && !ptrace_attached) {
 		dev_dbg(kfd_device, "Using KFD FD in wrong process\n");
 		retcode = -EBADF;
 		goto err_i1;
@@ -2013,6 +2752,19 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 		goto err_i1;
 	}
 
+	/*
+	 * Versions of docker shipped in Ubuntu 18.xx and 20.xx do not support
+	 * CAP_CHECKPOINT_RESTORE, so we also allow access if CAP_SYS_ADMIN as CAP_SYS_ADMIN is a
+	 * more priviledged access.
+	 */
+	if (unlikely(ioctl->flags & KFD_IOC_FLAG_CHECKPOINT_RESTORE)) {
+		if (!capable(CAP_CHECKPOINT_RESTORE) &&
+						!capable(CAP_SYS_ADMIN)) {
+			retcode = -EACCES;
+			goto err_i1;
+		}
+	}
+
 	if (cmd & (IOC_IN | IOC_OUT)) {
 		if (asize <= sizeof(stack_kdata)) {
 			kdata = stack_kdata;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 9624bbe8b501..bb6e49661d13 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1411,6 +1411,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 		case IP_VERSION(10, 1, 10):
 		case IP_VERSION(10, 1, 2):
 		case IP_VERSION(10, 1, 3):
+		case IP_VERSION(10, 1, 4):
 			pcache_info = navi10_cache_info;
 			num_of_cache_types = ARRAY_SIZE(navi10_cache_info);
 			break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
deleted file mode 100644
index 1e30717b5253..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ /dev/null
@@ -1,845 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/log2.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/device.h>
-
-#include "kfd_pm4_headers.h"
-#include "kfd_pm4_headers_diq.h"
-#include "kfd_kernel_queue.h"
-#include "kfd_priv.h"
-#include "kfd_pm4_opcodes.h"
-#include "cik_regs.h"
-#include "kfd_dbgmgr.h"
-#include "kfd_dbgdev.h"
-#include "kfd_device_queue_manager.h"
-
-static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
-{
-	dev->kfd2kgd->address_watch_disable(dev->adev);
-}
-
-static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
-				u32 pasid, uint64_t vmid0_address,
-				uint32_t *packet_buff, size_t size_in_bytes)
-{
-	struct pm4__release_mem *rm_packet;
-	struct pm4__indirect_buffer_pasid *ib_packet;
-	struct kfd_mem_obj *mem_obj;
-	size_t pq_packets_size_in_bytes;
-	union ULARGE_INTEGER *largep;
-	union ULARGE_INTEGER addr;
-	struct kernel_queue *kq;
-	uint64_t *rm_state;
-	unsigned int *ib_packet_buff;
-	int status;
-
-	if (WARN_ON(!size_in_bytes))
-		return -EINVAL;
-
-	kq = dbgdev->kq;
-
-	pq_packets_size_in_bytes = sizeof(struct pm4__release_mem) +
-				sizeof(struct pm4__indirect_buffer_pasid);
-
-	/*
-	 * We acquire a buffer from DIQ
-	 * The receive packet buff will be sitting on the Indirect Buffer
-	 * and in the PQ we put the IB packet + sync packet(s).
-	 */
-	status = kq_acquire_packet_buffer(kq,
-				pq_packets_size_in_bytes / sizeof(uint32_t),
-				&ib_packet_buff);
-	if (status) {
-		pr_err("kq_acquire_packet_buffer failed\n");
-		return status;
-	}
-
-	memset(ib_packet_buff, 0, pq_packets_size_in_bytes);
-
-	ib_packet = (struct pm4__indirect_buffer_pasid *) (ib_packet_buff);
-
-	ib_packet->header.count = 3;
-	ib_packet->header.opcode = IT_INDIRECT_BUFFER_PASID;
-	ib_packet->header.type = PM4_TYPE_3;
-
-	largep = (union ULARGE_INTEGER *) &vmid0_address;
-
-	ib_packet->bitfields2.ib_base_lo = largep->u.low_part >> 2;
-	ib_packet->bitfields3.ib_base_hi = largep->u.high_part;
-
-	ib_packet->control = (1 << 23) | (1 << 31) |
-			((size_in_bytes / 4) & 0xfffff);
-
-	ib_packet->bitfields5.pasid = pasid;
-
-	/*
-	 * for now we use release mem for GPU-CPU synchronization
-	 * Consider WaitRegMem + WriteData as a better alternative
-	 * we get a GART allocations ( gpu/cpu mapping),
-	 * for the sync variable, and wait until:
-	 * (a) Sync with HW
-	 * (b) Sync var is written by CP to mem.
-	 */
-	rm_packet = (struct pm4__release_mem *) (ib_packet_buff +
-			(sizeof(struct pm4__indirect_buffer_pasid) /
-					sizeof(unsigned int)));
-
-	status = kfd_gtt_sa_allocate(dbgdev->dev, sizeof(uint64_t),
-					&mem_obj);
-
-	if (status) {
-		pr_err("Failed to allocate GART memory\n");
-		kq_rollback_packet(kq);
-		return status;
-	}
-
-	rm_state = (uint64_t *) mem_obj->cpu_ptr;
-
-	*rm_state = QUEUESTATE__ACTIVE_COMPLETION_PENDING;
-
-	rm_packet->header.opcode = IT_RELEASE_MEM;
-	rm_packet->header.type = PM4_TYPE_3;
-	rm_packet->header.count = sizeof(struct pm4__release_mem) / 4 - 2;
-
-	rm_packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	rm_packet->bitfields2.event_index =
-				event_index___release_mem__end_of_pipe;
-
-	rm_packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
-	rm_packet->bitfields2.atc = 0;
-	rm_packet->bitfields2.tc_wb_action_ena = 1;
-
-	addr.quad_part = mem_obj->gpu_addr;
-
-	rm_packet->bitfields4.address_lo_32b = addr.u.low_part >> 2;
-	rm_packet->address_hi = addr.u.high_part;
-
-	rm_packet->bitfields3.data_sel =
-				data_sel___release_mem__send_64_bit_data;
-
-	rm_packet->bitfields3.int_sel =
-			int_sel___release_mem__send_data_after_write_confirm;
-
-	rm_packet->bitfields3.dst_sel =
-			dst_sel___release_mem__memory_controller;
-
-	rm_packet->data_lo = QUEUESTATE__ACTIVE;
-
-	kq_submit_packet(kq);
-
-	/* Wait till CP writes sync code: */
-	status = amdkfd_fence_wait_timeout(
-			rm_state,
-			QUEUESTATE__ACTIVE, 1500);
-
-	kfd_gtt_sa_free(dbgdev->dev, mem_obj);
-
-	return status;
-}
-
-static int dbgdev_register_nodiq(struct kfd_dbgdev *dbgdev)
-{
-	/*
-	 * no action is needed in this case,
-	 * just make sure diq will not be used
-	 */
-
-	dbgdev->kq = NULL;
-
-	return 0;
-}
-
-static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
-{
-	struct queue_properties properties;
-	unsigned int qid;
-	struct kernel_queue *kq = NULL;
-	int status;
-
-	properties.type = KFD_QUEUE_TYPE_DIQ;
-
-	status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
-				&properties, &qid, NULL);
-
-	if (status) {
-		pr_err("Failed to create DIQ\n");
-		return status;
-	}
-
-	pr_debug("DIQ Created with queue id: %d\n", qid);
-
-	kq = pqm_get_kernel_queue(dbgdev->pqm, qid);
-
-	if (!kq) {
-		pr_err("Error getting DIQ\n");
-		pqm_destroy_queue(dbgdev->pqm, qid);
-		return -EFAULT;
-	}
-
-	dbgdev->kq = kq;
-
-	return status;
-}
-
-static int dbgdev_unregister_nodiq(struct kfd_dbgdev *dbgdev)
-{
-	/* disable watch address */
-	dbgdev_address_watch_disable_nodiq(dbgdev->dev);
-	return 0;
-}
-
-static int dbgdev_unregister_diq(struct kfd_dbgdev *dbgdev)
-{
-	/* todo - disable address watch */
-	int status;
-
-	status = pqm_destroy_queue(dbgdev->pqm,
-			dbgdev->kq->queue->properties.queue_id);
-	dbgdev->kq = NULL;
-
-	return status;
-}
-
-static void dbgdev_address_watch_set_registers(
-			const struct dbg_address_watch_info *adw_info,
-			union TCP_WATCH_ADDR_H_BITS *addrHi,
-			union TCP_WATCH_ADDR_L_BITS *addrLo,
-			union TCP_WATCH_CNTL_BITS *cntl,
-			unsigned int index, unsigned int vmid)
-{
-	union ULARGE_INTEGER addr;
-
-	addr.quad_part = 0;
-	addrHi->u32All = 0;
-	addrLo->u32All = 0;
-	cntl->u32All = 0;
-
-	if (adw_info->watch_mask)
-		cntl->bitfields.mask =
-			(uint32_t) (adw_info->watch_mask[index] &
-					ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK);
-	else
-		cntl->bitfields.mask = ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK;
-
-	addr.quad_part = (unsigned long long) adw_info->watch_address[index];
-
-	addrHi->bitfields.addr = addr.u.high_part &
-					ADDRESS_WATCH_REG_ADDHIGH_MASK;
-	addrLo->bitfields.addr =
-			(addr.u.low_part >> ADDRESS_WATCH_REG_ADDLOW_SHIFT);
-
-	cntl->bitfields.mode = adw_info->watch_mode[index];
-	cntl->bitfields.vmid = (uint32_t) vmid;
-	/* for now assume it is an ATC address */
-	cntl->u32All |= ADDRESS_WATCH_REG_CNTL_ATC_BIT;
-
-	pr_debug("\t\t%20s %08x\n", "set reg mask :", cntl->bitfields.mask);
-	pr_debug("\t\t%20s %08x\n", "set reg add high :",
-			addrHi->bitfields.addr);
-	pr_debug("\t\t%20s %08x\n", "set reg add low :",
-			addrLo->bitfields.addr);
-}
-
-static int dbgdev_address_watch_nodiq(struct kfd_dbgdev *dbgdev,
-				      struct dbg_address_watch_info *adw_info)
-{
-	union TCP_WATCH_ADDR_H_BITS addrHi;
-	union TCP_WATCH_ADDR_L_BITS addrLo;
-	union TCP_WATCH_CNTL_BITS cntl;
-	struct kfd_process_device *pdd;
-	unsigned int i;
-
-	/* taking the vmid for that process on the safe way using pdd */
-	pdd = kfd_get_process_device_data(dbgdev->dev,
-					adw_info->process);
-	if (!pdd) {
-		pr_err("Failed to get pdd for wave control no DIQ\n");
-		return -EFAULT;
-	}
-
-	addrHi.u32All = 0;
-	addrLo.u32All = 0;
-	cntl.u32All = 0;
-
-	if ((adw_info->num_watch_points > MAX_WATCH_ADDRESSES) ||
-			(adw_info->num_watch_points == 0)) {
-		pr_err("num_watch_points is invalid\n");
-		return -EINVAL;
-	}
-
-	if (!adw_info->watch_mode || !adw_info->watch_address) {
-		pr_err("adw_info fields are not valid\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < adw_info->num_watch_points; i++) {
-		dbgdev_address_watch_set_registers(adw_info, &addrHi, &addrLo,
-						&cntl, i, pdd->qpd.vmid);
-
-		pr_debug("\t\t%30s\n", "* * * * * * * * * * * * * * * * * *");
-		pr_debug("\t\t%20s %08x\n", "register index :", i);
-		pr_debug("\t\t%20s %08x\n", "vmid is :", pdd->qpd.vmid);
-		pr_debug("\t\t%20s %08x\n", "Address Low is :",
-				addrLo.bitfields.addr);
-		pr_debug("\t\t%20s %08x\n", "Address high is :",
-				addrHi.bitfields.addr);
-		pr_debug("\t\t%20s %08x\n", "Address high is :",
-				addrHi.bitfields.addr);
-		pr_debug("\t\t%20s %08x\n", "Control Mask is :",
-				cntl.bitfields.mask);
-		pr_debug("\t\t%20s %08x\n", "Control Mode is :",
-				cntl.bitfields.mode);
-		pr_debug("\t\t%20s %08x\n", "Control Vmid is :",
-				cntl.bitfields.vmid);
-		pr_debug("\t\t%20s %08x\n", "Control atc  is :",
-				cntl.bitfields.atc);
-		pr_debug("\t\t%30s\n", "* * * * * * * * * * * * * * * * * *");
-
-		pdd->dev->kfd2kgd->address_watch_execute(
-						dbgdev->dev->adev,
-						i,
-						cntl.u32All,
-						addrHi.u32All,
-						addrLo.u32All);
-	}
-
-	return 0;
-}
-
-static int dbgdev_address_watch_diq(struct kfd_dbgdev *dbgdev,
-				    struct dbg_address_watch_info *adw_info)
-{
-	struct pm4__set_config_reg *packets_vec;
-	union TCP_WATCH_ADDR_H_BITS addrHi;
-	union TCP_WATCH_ADDR_L_BITS addrLo;
-	union TCP_WATCH_CNTL_BITS cntl;
-	struct kfd_mem_obj *mem_obj;
-	unsigned int aw_reg_add_dword;
-	uint32_t *packet_buff_uint;
-	unsigned int i;
-	int status;
-	size_t ib_size = sizeof(struct pm4__set_config_reg) * 4;
-	/* we do not control the vmid in DIQ mode, just a place holder */
-	unsigned int vmid = 0;
-
-	addrHi.u32All = 0;
-	addrLo.u32All = 0;
-	cntl.u32All = 0;
-
-	if ((adw_info->num_watch_points > MAX_WATCH_ADDRESSES) ||
-			(adw_info->num_watch_points == 0)) {
-		pr_err("num_watch_points is invalid\n");
-		return -EINVAL;
-	}
-
-	if (!adw_info->watch_mode || !adw_info->watch_address) {
-		pr_err("adw_info fields are not valid\n");
-		return -EINVAL;
-	}
-
-	status = kfd_gtt_sa_allocate(dbgdev->dev, ib_size, &mem_obj);
-
-	if (status) {
-		pr_err("Failed to allocate GART memory\n");
-		return status;
-	}
-
-	packet_buff_uint = mem_obj->cpu_ptr;
-
-	memset(packet_buff_uint, 0, ib_size);
-
-	packets_vec = (struct pm4__set_config_reg *) (packet_buff_uint);
-
-	packets_vec[0].header.count = 1;
-	packets_vec[0].header.opcode = IT_SET_CONFIG_REG;
-	packets_vec[0].header.type = PM4_TYPE_3;
-	packets_vec[0].bitfields2.vmid_shift = ADDRESS_WATCH_CNTL_OFFSET;
-	packets_vec[0].bitfields2.insert_vmid = 1;
-	packets_vec[1].ordinal1 = packets_vec[0].ordinal1;
-	packets_vec[1].bitfields2.insert_vmid = 0;
-	packets_vec[2].ordinal1 = packets_vec[0].ordinal1;
-	packets_vec[2].bitfields2.insert_vmid = 0;
-	packets_vec[3].ordinal1 = packets_vec[0].ordinal1;
-	packets_vec[3].bitfields2.vmid_shift = ADDRESS_WATCH_CNTL_OFFSET;
-	packets_vec[3].bitfields2.insert_vmid = 1;
-
-	for (i = 0; i < adw_info->num_watch_points; i++) {
-		dbgdev_address_watch_set_registers(adw_info,
-						&addrHi,
-						&addrLo,
-						&cntl,
-						i,
-						vmid);
-
-		pr_debug("\t\t%30s\n", "* * * * * * * * * * * * * * * * * *");
-		pr_debug("\t\t%20s %08x\n", "register index :", i);
-		pr_debug("\t\t%20s %08x\n", "vmid is :", vmid);
-		pr_debug("\t\t%20s %p\n", "Add ptr is :",
-				adw_info->watch_address);
-		pr_debug("\t\t%20s %08llx\n", "Add     is :",
-				adw_info->watch_address[i]);
-		pr_debug("\t\t%20s %08x\n", "Address Low is :",
-				addrLo.bitfields.addr);
-		pr_debug("\t\t%20s %08x\n", "Address high is :",
-				addrHi.bitfields.addr);
-		pr_debug("\t\t%20s %08x\n", "Control Mask is :",
-				cntl.bitfields.mask);
-		pr_debug("\t\t%20s %08x\n", "Control Mode is :",
-				cntl.bitfields.mode);
-		pr_debug("\t\t%20s %08x\n", "Control Vmid is :",
-				cntl.bitfields.vmid);
-		pr_debug("\t\t%20s %08x\n", "Control atc  is :",
-				cntl.bitfields.atc);
-		pr_debug("\t\t%30s\n", "* * * * * * * * * * * * * * * * * *");
-
-		aw_reg_add_dword =
-				dbgdev->dev->kfd2kgd->address_watch_get_offset(
-					dbgdev->dev->adev,
-					i,
-					ADDRESS_WATCH_REG_CNTL);
-
-		packets_vec[0].bitfields2.reg_offset =
-					aw_reg_add_dword - AMD_CONFIG_REG_BASE;
-
-		packets_vec[0].reg_data[0] = cntl.u32All;
-
-		aw_reg_add_dword =
-				dbgdev->dev->kfd2kgd->address_watch_get_offset(
-					dbgdev->dev->adev,
-					i,
-					ADDRESS_WATCH_REG_ADDR_HI);
-
-		packets_vec[1].bitfields2.reg_offset =
-					aw_reg_add_dword - AMD_CONFIG_REG_BASE;
-		packets_vec[1].reg_data[0] = addrHi.u32All;
-
-		aw_reg_add_dword =
-				dbgdev->dev->kfd2kgd->address_watch_get_offset(
-					dbgdev->dev->adev,
-					i,
-					ADDRESS_WATCH_REG_ADDR_LO);
-
-		packets_vec[2].bitfields2.reg_offset =
-				aw_reg_add_dword - AMD_CONFIG_REG_BASE;
-		packets_vec[2].reg_data[0] = addrLo.u32All;
-
-		/* enable watch flag if address is not zero*/
-		if (adw_info->watch_address[i] > 0)
-			cntl.bitfields.valid = 1;
-		else
-			cntl.bitfields.valid = 0;
-
-		aw_reg_add_dword =
-				dbgdev->dev->kfd2kgd->address_watch_get_offset(
-					dbgdev->dev->adev,
-					i,
-					ADDRESS_WATCH_REG_CNTL);
-
-		packets_vec[3].bitfields2.reg_offset =
-					aw_reg_add_dword - AMD_CONFIG_REG_BASE;
-		packets_vec[3].reg_data[0] = cntl.u32All;
-
-		status = dbgdev_diq_submit_ib(
-					dbgdev,
-					adw_info->process->pasid,
-					mem_obj->gpu_addr,
-					packet_buff_uint,
-					ib_size);
-
-		if (status) {
-			pr_err("Failed to submit IB to DIQ\n");
-			break;
-		}
-	}
-
-	kfd_gtt_sa_free(dbgdev->dev, mem_obj);
-	return status;
-}
-
-static int dbgdev_wave_control_set_registers(
-				struct dbg_wave_control_info *wac_info,
-				union SQ_CMD_BITS *in_reg_sq_cmd,
-				union GRBM_GFX_INDEX_BITS *in_reg_gfx_index)
-{
-	int status = 0;
-	union SQ_CMD_BITS reg_sq_cmd;
-	union GRBM_GFX_INDEX_BITS reg_gfx_index;
-	struct HsaDbgWaveMsgAMDGen2 *pMsg;
-
-	reg_sq_cmd.u32All = 0;
-	reg_gfx_index.u32All = 0;
-	pMsg = &wac_info->dbgWave_msg.DbgWaveMsg.WaveMsgInfoGen2;
-
-	switch (wac_info->mode) {
-	/* Send command to single wave */
-	case HSA_DBG_WAVEMODE_SINGLE:
-		/*
-		 * Limit access to the process waves only,
-		 * by setting vmid check
-		 */
-		reg_sq_cmd.bits.check_vmid = 1;
-		reg_sq_cmd.bits.simd_id = pMsg->ui32.SIMD;
-		reg_sq_cmd.bits.wave_id = pMsg->ui32.WaveId;
-		reg_sq_cmd.bits.mode = SQ_IND_CMD_MODE_SINGLE;
-
-		reg_gfx_index.bits.sh_index = pMsg->ui32.ShaderArray;
-		reg_gfx_index.bits.se_index = pMsg->ui32.ShaderEngine;
-		reg_gfx_index.bits.instance_index = pMsg->ui32.HSACU;
-
-		break;
-
-	/* Send command to all waves with matching VMID */
-	case HSA_DBG_WAVEMODE_BROADCAST_PROCESS:
-
-		reg_gfx_index.bits.sh_broadcast_writes = 1;
-		reg_gfx_index.bits.se_broadcast_writes = 1;
-		reg_gfx_index.bits.instance_broadcast_writes = 1;
-
-		reg_sq_cmd.bits.mode = SQ_IND_CMD_MODE_BROADCAST;
-
-		break;
-
-	/* Send command to all CU waves with matching VMID */
-	case HSA_DBG_WAVEMODE_BROADCAST_PROCESS_CU:
-
-		reg_sq_cmd.bits.check_vmid = 1;
-		reg_sq_cmd.bits.mode = SQ_IND_CMD_MODE_BROADCAST;
-
-		reg_gfx_index.bits.sh_index = pMsg->ui32.ShaderArray;
-		reg_gfx_index.bits.se_index = pMsg->ui32.ShaderEngine;
-		reg_gfx_index.bits.instance_index = pMsg->ui32.HSACU;
-
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	switch (wac_info->operand) {
-	case HSA_DBG_WAVEOP_HALT:
-		reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_HALT;
-		break;
-
-	case HSA_DBG_WAVEOP_RESUME:
-		reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_RESUME;
-		break;
-
-	case HSA_DBG_WAVEOP_KILL:
-		reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_KILL;
-		break;
-
-	case HSA_DBG_WAVEOP_DEBUG:
-		reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_DEBUG;
-		break;
-
-	case HSA_DBG_WAVEOP_TRAP:
-		if (wac_info->trapId < MAX_TRAPID) {
-			reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_TRAP;
-			reg_sq_cmd.bits.trap_id = wac_info->trapId;
-		} else {
-			status = -EINVAL;
-		}
-		break;
-
-	default:
-		status = -EINVAL;
-		break;
-	}
-
-	if (status == 0) {
-		*in_reg_sq_cmd = reg_sq_cmd;
-		*in_reg_gfx_index = reg_gfx_index;
-	}
-
-	return status;
-}
-
-static int dbgdev_wave_control_diq(struct kfd_dbgdev *dbgdev,
-					struct dbg_wave_control_info *wac_info)
-{
-
-	int status;
-	union SQ_CMD_BITS reg_sq_cmd;
-	union GRBM_GFX_INDEX_BITS reg_gfx_index;
-	struct kfd_mem_obj *mem_obj;
-	uint32_t *packet_buff_uint;
-	struct pm4__set_config_reg *packets_vec;
-	size_t ib_size = sizeof(struct pm4__set_config_reg) * 3;
-
-	reg_sq_cmd.u32All = 0;
-
-	status = dbgdev_wave_control_set_registers(wac_info, &reg_sq_cmd,
-							&reg_gfx_index);
-	if (status) {
-		pr_err("Failed to set wave control registers\n");
-		return status;
-	}
-
-	/* we do not control the VMID in DIQ, so reset it to a known value */
-	reg_sq_cmd.bits.vm_id = 0;
-
-	pr_debug("\t\t %30s\n", "* * * * * * * * * * * * * * * * * *");
-
-	pr_debug("\t\t mode      is: %u\n", wac_info->mode);
-	pr_debug("\t\t operand   is: %u\n", wac_info->operand);
-	pr_debug("\t\t trap id   is: %u\n", wac_info->trapId);
-	pr_debug("\t\t msg value is: %u\n",
-			wac_info->dbgWave_msg.DbgWaveMsg.WaveMsgInfoGen2.Value);
-	pr_debug("\t\t vmid      is: N/A\n");
-
-	pr_debug("\t\t chk_vmid  is : %u\n", reg_sq_cmd.bitfields.check_vmid);
-	pr_debug("\t\t command   is : %u\n", reg_sq_cmd.bitfields.cmd);
-	pr_debug("\t\t queue id  is : %u\n", reg_sq_cmd.bitfields.queue_id);
-	pr_debug("\t\t simd id   is : %u\n", reg_sq_cmd.bitfields.simd_id);
-	pr_debug("\t\t mode      is : %u\n", reg_sq_cmd.bitfields.mode);
-	pr_debug("\t\t vm_id     is : %u\n", reg_sq_cmd.bitfields.vm_id);
-	pr_debug("\t\t wave_id   is : %u\n", reg_sq_cmd.bitfields.wave_id);
-
-	pr_debug("\t\t ibw       is : %u\n",
-			reg_gfx_index.bitfields.instance_broadcast_writes);
-	pr_debug("\t\t ii        is : %u\n",
-			reg_gfx_index.bitfields.instance_index);
-	pr_debug("\t\t sebw      is : %u\n",
-			reg_gfx_index.bitfields.se_broadcast_writes);
-	pr_debug("\t\t se_ind    is : %u\n", reg_gfx_index.bitfields.se_index);
-	pr_debug("\t\t sh_ind    is : %u\n", reg_gfx_index.bitfields.sh_index);
-	pr_debug("\t\t sbw       is : %u\n",
-			reg_gfx_index.bitfields.sh_broadcast_writes);
-
-	pr_debug("\t\t %30s\n", "* * * * * * * * * * * * * * * * * *");
-
-	status = kfd_gtt_sa_allocate(dbgdev->dev, ib_size, &mem_obj);
-
-	if (status != 0) {
-		pr_err("Failed to allocate GART memory\n");
-		return status;
-	}
-
-	packet_buff_uint = mem_obj->cpu_ptr;
-
-	memset(packet_buff_uint, 0, ib_size);
-
-	packets_vec =  (struct pm4__set_config_reg *) packet_buff_uint;
-	packets_vec[0].header.count = 1;
-	packets_vec[0].header.opcode = IT_SET_UCONFIG_REG;
-	packets_vec[0].header.type = PM4_TYPE_3;
-	packets_vec[0].bitfields2.reg_offset =
-			GRBM_GFX_INDEX / 4 - USERCONFIG_REG_BASE;
-
-	packets_vec[0].bitfields2.insert_vmid = 0;
-	packets_vec[0].reg_data[0] = reg_gfx_index.u32All;
-
-	packets_vec[1].header.count = 1;
-	packets_vec[1].header.opcode = IT_SET_CONFIG_REG;
-	packets_vec[1].header.type = PM4_TYPE_3;
-	packets_vec[1].bitfields2.reg_offset = SQ_CMD / 4 - AMD_CONFIG_REG_BASE;
-
-	packets_vec[1].bitfields2.vmid_shift = SQ_CMD_VMID_OFFSET;
-	packets_vec[1].bitfields2.insert_vmid = 1;
-	packets_vec[1].reg_data[0] = reg_sq_cmd.u32All;
-
-	/* Restore the GRBM_GFX_INDEX register */
-
-	reg_gfx_index.u32All = 0;
-	reg_gfx_index.bits.sh_broadcast_writes = 1;
-	reg_gfx_index.bits.instance_broadcast_writes = 1;
-	reg_gfx_index.bits.se_broadcast_writes = 1;
-
-
-	packets_vec[2].ordinal1 = packets_vec[0].ordinal1;
-	packets_vec[2].bitfields2.reg_offset =
-				GRBM_GFX_INDEX / 4 - USERCONFIG_REG_BASE;
-
-	packets_vec[2].bitfields2.insert_vmid = 0;
-	packets_vec[2].reg_data[0] = reg_gfx_index.u32All;
-
-	status = dbgdev_diq_submit_ib(
-			dbgdev,
-			wac_info->process->pasid,
-			mem_obj->gpu_addr,
-			packet_buff_uint,
-			ib_size);
-
-	if (status)
-		pr_err("Failed to submit IB to DIQ\n");
-
-	kfd_gtt_sa_free(dbgdev->dev, mem_obj);
-
-	return status;
-}
-
-static int dbgdev_wave_control_nodiq(struct kfd_dbgdev *dbgdev,
-					struct dbg_wave_control_info *wac_info)
-{
-	int status;
-	union SQ_CMD_BITS reg_sq_cmd;
-	union GRBM_GFX_INDEX_BITS reg_gfx_index;
-	struct kfd_process_device *pdd;
-
-	reg_sq_cmd.u32All = 0;
-
-	/* taking the VMID for that process on the safe way using PDD */
-	pdd = kfd_get_process_device_data(dbgdev->dev, wac_info->process);
-
-	if (!pdd) {
-		pr_err("Failed to get pdd for wave control no DIQ\n");
-		return -EFAULT;
-	}
-	status = dbgdev_wave_control_set_registers(wac_info, &reg_sq_cmd,
-							&reg_gfx_index);
-	if (status) {
-		pr_err("Failed to set wave control registers\n");
-		return status;
-	}
-
-	/* for non DIQ we need to patch the VMID: */
-
-	reg_sq_cmd.bits.vm_id = pdd->qpd.vmid;
-
-	pr_debug("\t\t %30s\n", "* * * * * * * * * * * * * * * * * *");
-
-	pr_debug("\t\t mode      is: %u\n", wac_info->mode);
-	pr_debug("\t\t operand   is: %u\n", wac_info->operand);
-	pr_debug("\t\t trap id   is: %u\n", wac_info->trapId);
-	pr_debug("\t\t msg value is: %u\n",
-			wac_info->dbgWave_msg.DbgWaveMsg.WaveMsgInfoGen2.Value);
-	pr_debug("\t\t vmid      is: %u\n", pdd->qpd.vmid);
-
-	pr_debug("\t\t chk_vmid  is : %u\n", reg_sq_cmd.bitfields.check_vmid);
-	pr_debug("\t\t command   is : %u\n", reg_sq_cmd.bitfields.cmd);
-	pr_debug("\t\t queue id  is : %u\n", reg_sq_cmd.bitfields.queue_id);
-	pr_debug("\t\t simd id   is : %u\n", reg_sq_cmd.bitfields.simd_id);
-	pr_debug("\t\t mode      is : %u\n", reg_sq_cmd.bitfields.mode);
-	pr_debug("\t\t vm_id     is : %u\n", reg_sq_cmd.bitfields.vm_id);
-	pr_debug("\t\t wave_id   is : %u\n", reg_sq_cmd.bitfields.wave_id);
-
-	pr_debug("\t\t ibw       is : %u\n",
-			reg_gfx_index.bitfields.instance_broadcast_writes);
-	pr_debug("\t\t ii        is : %u\n",
-			reg_gfx_index.bitfields.instance_index);
-	pr_debug("\t\t sebw      is : %u\n",
-			reg_gfx_index.bitfields.se_broadcast_writes);
-	pr_debug("\t\t se_ind    is : %u\n", reg_gfx_index.bitfields.se_index);
-	pr_debug("\t\t sh_ind    is : %u\n", reg_gfx_index.bitfields.sh_index);
-	pr_debug("\t\t sbw       is : %u\n",
-			reg_gfx_index.bitfields.sh_broadcast_writes);
-
-	pr_debug("\t\t %30s\n", "* * * * * * * * * * * * * * * * * *");
-
-	return dbgdev->dev->kfd2kgd->wave_control_execute(dbgdev->dev->adev,
-							reg_gfx_index.u32All,
-							reg_sq_cmd.u32All);
-}
-
-int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
-{
-	int status = 0;
-	unsigned int vmid;
-	uint16_t queried_pasid;
-	union SQ_CMD_BITS reg_sq_cmd;
-	union GRBM_GFX_INDEX_BITS reg_gfx_index;
-	struct kfd_process_device *pdd;
-	struct dbg_wave_control_info wac_info;
-	int first_vmid_to_scan = dev->vm_info.first_vmid_kfd;
-	int last_vmid_to_scan = dev->vm_info.last_vmid_kfd;
-
-	reg_sq_cmd.u32All = 0;
-	status = 0;
-
-	wac_info.mode = HSA_DBG_WAVEMODE_BROADCAST_PROCESS;
-	wac_info.operand = HSA_DBG_WAVEOP_KILL;
-
-	pr_debug("Killing all process wavefronts\n");
-
-	/* Scan all registers in the range ATC_VMID8_PASID_MAPPING ..
-	 * ATC_VMID15_PASID_MAPPING
-	 * to check which VMID the current process is mapped to.
-	 */
-
-	for (vmid = first_vmid_to_scan; vmid <= last_vmid_to_scan; vmid++) {
-		status = dev->kfd2kgd->get_atc_vmid_pasid_mapping_info
-				(dev->adev, vmid, &queried_pasid);
-
-		if (status && queried_pasid == p->pasid) {
-			pr_debug("Killing wave fronts of vmid %d and pasid 0x%x\n",
-					vmid, p->pasid);
-			break;
-		}
-	}
-
-	if (vmid > last_vmid_to_scan) {
-		pr_err("Didn't find vmid for pasid 0x%x\n", p->pasid);
-		return -EFAULT;
-	}
-
-	/* taking the VMID for that process on the safe way using PDD */
-	pdd = kfd_get_process_device_data(dev, p);
-	if (!pdd)
-		return -EFAULT;
-
-	status = dbgdev_wave_control_set_registers(&wac_info, &reg_sq_cmd,
-			&reg_gfx_index);
-	if (status != 0)
-		return -EINVAL;
-
-	/* for non DIQ we need to patch the VMID: */
-	reg_sq_cmd.bits.vm_id = vmid;
-
-	dev->kfd2kgd->wave_control_execute(dev->adev,
-					reg_gfx_index.u32All,
-					reg_sq_cmd.u32All);
-
-	return 0;
-}
-
-void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev,
-			enum DBGDEV_TYPE type)
-{
-	pdbgdev->dev = pdev;
-	pdbgdev->kq = NULL;
-	pdbgdev->type = type;
-	pdbgdev->pqm = NULL;
-
-	switch (type) {
-	case DBGDEV_TYPE_NODIQ:
-		pdbgdev->dbgdev_register = dbgdev_register_nodiq;
-		pdbgdev->dbgdev_unregister = dbgdev_unregister_nodiq;
-		pdbgdev->dbgdev_wave_control = dbgdev_wave_control_nodiq;
-		pdbgdev->dbgdev_address_watch = dbgdev_address_watch_nodiq;
-		break;
-	case DBGDEV_TYPE_DIQ:
-	default:
-		pdbgdev->dbgdev_register = dbgdev_register_diq;
-		pdbgdev->dbgdev_unregister = dbgdev_unregister_diq;
-		pdbgdev->dbgdev_wave_control =  dbgdev_wave_control_diq;
-		pdbgdev->dbgdev_address_watch = dbgdev_address_watch_diq;
-		break;
-	}
-
-}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
deleted file mode 100644
index 0619c777b47e..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
+++ /dev/null
@@ -1,230 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef KFD_DBGDEV_H_
-#define KFD_DBGDEV_H_
-
-enum {
-	SQ_CMD_VMID_OFFSET = 28,
-	ADDRESS_WATCH_CNTL_OFFSET = 24
-};
-
-enum {
-	PRIV_QUEUE_SYNC_TIME_MS = 200
-};
-
-/* CONTEXT reg space definition */
-enum {
-	CONTEXT_REG_BASE = 0xA000,
-	CONTEXT_REG_END = 0xA400,
-	CONTEXT_REG_SIZE = CONTEXT_REG_END - CONTEXT_REG_BASE
-};
-
-/* USER CONFIG reg space definition */
-enum {
-	USERCONFIG_REG_BASE = 0xC000,
-	USERCONFIG_REG_END = 0x10000,
-	USERCONFIG_REG_SIZE = USERCONFIG_REG_END - USERCONFIG_REG_BASE
-};
-
-/* CONFIG reg space definition */
-enum {
-	AMD_CONFIG_REG_BASE = 0x2000,	/* in dwords */
-	AMD_CONFIG_REG_END = 0x2B00,
-	AMD_CONFIG_REG_SIZE = AMD_CONFIG_REG_END - AMD_CONFIG_REG_BASE
-};
-
-/* SH reg space definition */
-enum {
-	SH_REG_BASE = 0x2C00,
-	SH_REG_END = 0x3000,
-	SH_REG_SIZE = SH_REG_END - SH_REG_BASE
-};
-
-/* SQ_CMD definitions */
-#define SQ_CMD						0x8DEC
-
-enum SQ_IND_CMD_CMD {
-	SQ_IND_CMD_CMD_NULL = 0x00000000,
-	SQ_IND_CMD_CMD_HALT = 0x00000001,
-	SQ_IND_CMD_CMD_RESUME = 0x00000002,
-	SQ_IND_CMD_CMD_KILL = 0x00000003,
-	SQ_IND_CMD_CMD_DEBUG = 0x00000004,
-	SQ_IND_CMD_CMD_TRAP = 0x00000005,
-};
-
-enum SQ_IND_CMD_MODE {
-	SQ_IND_CMD_MODE_SINGLE = 0x00000000,
-	SQ_IND_CMD_MODE_BROADCAST = 0x00000001,
-	SQ_IND_CMD_MODE_BROADCAST_QUEUE = 0x00000002,
-	SQ_IND_CMD_MODE_BROADCAST_PIPE = 0x00000003,
-	SQ_IND_CMD_MODE_BROADCAST_ME = 0x00000004,
-};
-
-union SQ_IND_INDEX_BITS {
-	struct {
-		uint32_t wave_id:4;
-		uint32_t simd_id:2;
-		uint32_t thread_id:6;
-		 uint32_t:1;
-		uint32_t force_read:1;
-		uint32_t read_timeout:1;
-		uint32_t unindexed:1;
-		uint32_t index:16;
-
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union SQ_IND_CMD_BITS {
-	struct {
-		uint32_t data:32;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union SQ_CMD_BITS {
-	struct {
-		uint32_t cmd:3;
-		 uint32_t:1;
-		uint32_t mode:3;
-		uint32_t check_vmid:1;
-		uint32_t trap_id:3;
-		 uint32_t:5;
-		uint32_t wave_id:4;
-		uint32_t simd_id:2;
-		 uint32_t:2;
-		uint32_t queue_id:3;
-		 uint32_t:1;
-		uint32_t vm_id:4;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union SQ_IND_DATA_BITS {
-	struct {
-		uint32_t data:32;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union GRBM_GFX_INDEX_BITS {
-	struct {
-		uint32_t instance_index:8;
-		uint32_t sh_index:8;
-		uint32_t se_index:8;
-		 uint32_t:5;
-		uint32_t sh_broadcast_writes:1;
-		uint32_t instance_broadcast_writes:1;
-		uint32_t se_broadcast_writes:1;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union TCP_WATCH_ADDR_H_BITS {
-	struct {
-		uint32_t addr:16;
-		 uint32_t:16;
-
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-union TCP_WATCH_ADDR_L_BITS {
-	struct {
-		uint32_t:6;
-		uint32_t addr:26;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-enum {
-	QUEUESTATE__INVALID = 0, /* so by default we'll get invalid state */
-	QUEUESTATE__ACTIVE_COMPLETION_PENDING,
-	QUEUESTATE__ACTIVE
-};
-
-union ULARGE_INTEGER {
-	struct {
-		uint32_t low_part;
-		uint32_t high_part;
-	} u;
-	unsigned long long quad_part;
-};
-
-
-#define KFD_CIK_VMID_START_OFFSET (8)
-#define KFD_CIK_VMID_END_OFFSET (KFD_CIK_VMID_START_OFFSET + (8))
-
-
-void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev,
-			enum DBGDEV_TYPE type);
-
-union TCP_WATCH_CNTL_BITS {
-	struct {
-		uint32_t mask:24;
-		uint32_t vmid:4;
-		uint32_t atc:1;
-		uint32_t mode:2;
-		uint32_t valid:1;
-	} bitfields, bits;
-	uint32_t u32All;
-	signed int i32All;
-	float f32All;
-};
-
-enum {
-	ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL,
-	ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF,
-	ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000,
-	/* extend the mask to 26 bits in order to match the low address field */
-	ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6,
-	ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF
-};
-
-enum {
-	MAX_TRAPID = 8,		/* 3 bits in the bitfield. */
-	MAX_WATCH_ADDRESSES = 4
-};
-
-enum {
-	ADDRESS_WATCH_REG_ADDR_HI = 0,
-	ADDRESS_WATCH_REG_ADDR_LO,
-	ADDRESS_WATCH_REG_CNTL,
-	ADDRESS_WATCH_REG_MAX
-};
-
-#endif	/* KFD_DBGDEV_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
deleted file mode 100644
index 9bfa50633654..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
+++ /dev/null
@@ -1,158 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/log2.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/device.h>
-
-#include "kfd_priv.h"
-#include "cik_regs.h"
-#include "kfd_pm4_headers.h"
-#include "kfd_pm4_headers_diq.h"
-#include "kfd_dbgmgr.h"
-#include "kfd_dbgdev.h"
-#include "kfd_device_queue_manager.h"
-
-static DEFINE_MUTEX(kfd_dbgmgr_mutex);
-
-struct mutex *kfd_get_dbgmgr_mutex(void)
-{
-	return &kfd_dbgmgr_mutex;
-}
-
-
-static void kfd_dbgmgr_uninitialize(struct kfd_dbgmgr *pmgr)
-{
-	kfree(pmgr->dbgdev);
-
-	pmgr->dbgdev = NULL;
-	pmgr->pasid = 0;
-	pmgr->dev = NULL;
-}
-
-void kfd_dbgmgr_destroy(struct kfd_dbgmgr *pmgr)
-{
-	if (pmgr) {
-		kfd_dbgmgr_uninitialize(pmgr);
-		kfree(pmgr);
-	}
-}
-
-bool kfd_dbgmgr_create(struct kfd_dbgmgr **ppmgr, struct kfd_dev *pdev)
-{
-	enum DBGDEV_TYPE type = DBGDEV_TYPE_DIQ;
-	struct kfd_dbgmgr *new_buff;
-
-	if (WARN_ON(!pdev->init_complete))
-		return false;
-
-	new_buff = kfd_alloc_struct(new_buff);
-	if (!new_buff) {
-		pr_err("Failed to allocate dbgmgr instance\n");
-		return false;
-	}
-
-	new_buff->pasid = 0;
-	new_buff->dev = pdev;
-	new_buff->dbgdev = kfd_alloc_struct(new_buff->dbgdev);
-	if (!new_buff->dbgdev) {
-		pr_err("Failed to allocate dbgdev instance\n");
-		kfree(new_buff);
-		return false;
-	}
-
-	/* get actual type of DBGDevice cpsch or not */
-	if (pdev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS)
-		type = DBGDEV_TYPE_NODIQ;
-
-	kfd_dbgdev_init(new_buff->dbgdev, pdev, type);
-	*ppmgr = new_buff;
-
-	return true;
-}
-
-long kfd_dbgmgr_register(struct kfd_dbgmgr *pmgr, struct kfd_process *p)
-{
-	if (pmgr->pasid != 0) {
-		pr_debug("H/W debugger is already active using pasid 0x%x\n",
-				pmgr->pasid);
-		return -EBUSY;
-	}
-
-	/* remember pasid */
-	pmgr->pasid = p->pasid;
-
-	/* provide the pqm for diq generation */
-	pmgr->dbgdev->pqm = &p->pqm;
-
-	/* activate the actual registering */
-	pmgr->dbgdev->dbgdev_register(pmgr->dbgdev);
-
-	return 0;
-}
-
-long kfd_dbgmgr_unregister(struct kfd_dbgmgr *pmgr, struct kfd_process *p)
-{
-	/* Is the requests coming from the already registered process? */
-	if (pmgr->pasid != p->pasid) {
-		pr_debug("H/W debugger is not registered by calling pasid 0x%x\n",
-				p->pasid);
-		return -EINVAL;
-	}
-
-	pmgr->dbgdev->dbgdev_unregister(pmgr->dbgdev);
-
-	pmgr->pasid = 0;
-
-	return 0;
-}
-
-long kfd_dbgmgr_wave_control(struct kfd_dbgmgr *pmgr,
-				struct dbg_wave_control_info *wac_info)
-{
-	/* Is the requests coming from the already registered process? */
-	if (pmgr->pasid != wac_info->process->pasid) {
-		pr_debug("H/W debugger support was not registered for requester pasid 0x%x\n",
-				wac_info->process->pasid);
-		return -EINVAL;
-	}
-
-	return (long) pmgr->dbgdev->dbgdev_wave_control(pmgr->dbgdev, wac_info);
-}
-
-long kfd_dbgmgr_address_watch(struct kfd_dbgmgr *pmgr,
-				struct dbg_address_watch_info *adw_info)
-{
-	/* Is the requests coming from the already registered process? */
-	if (pmgr->pasid != adw_info->process->pasid) {
-		pr_debug("H/W debugger support was not registered for requester pasid 0x%x\n",
-				adw_info->process->pasid);
-		return -EINVAL;
-	}
-
-	return (long) pmgr->dbgdev->dbgdev_address_watch(pmgr->dbgdev,
-							adw_info);
-}
-
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
deleted file mode 100644
index f9c6df1fdc5c..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
+++ /dev/null
@@ -1,293 +0,0 @@
-/*
- * Copyright 2014 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#ifndef KFD_DBGMGR_H_
-#define KFD_DBGMGR_H_
-
-#include "kfd_priv.h"
-
-/* must align with hsakmttypes definition */
-#pragma pack(push, 4)
-
-enum HSA_DBG_WAVEOP {
-	HSA_DBG_WAVEOP_HALT = 1,   /* Halts a wavefront */
-	HSA_DBG_WAVEOP_RESUME = 2, /* Resumes a wavefront */
-	HSA_DBG_WAVEOP_KILL = 3,   /* Kills a wavefront */
-	HSA_DBG_WAVEOP_DEBUG = 4,  /* Causes wavefront to enter dbg mode */
-	HSA_DBG_WAVEOP_TRAP = 5,   /* Causes wavefront to take a trap */
-	HSA_DBG_NUM_WAVEOP = 5,
-	HSA_DBG_MAX_WAVEOP = 0xFFFFFFFF
-};
-
-enum HSA_DBG_WAVEMODE {
-	/* send command to a single wave */
-	HSA_DBG_WAVEMODE_SINGLE = 0,
-	/*
-	 * Broadcast to all wavefronts of all processes is not
-	 * supported for HSA user mode
-	 */
-
-	/* send to waves within current process */
-	HSA_DBG_WAVEMODE_BROADCAST_PROCESS = 2,
-	/* send to waves within current process on CU  */
-	HSA_DBG_WAVEMODE_BROADCAST_PROCESS_CU = 3,
-	HSA_DBG_NUM_WAVEMODE = 3,
-	HSA_DBG_MAX_WAVEMODE = 0xFFFFFFFF
-};
-
-enum HSA_DBG_WAVEMSG_TYPE {
-	HSA_DBG_WAVEMSG_AUTO = 0,
-	HSA_DBG_WAVEMSG_USER = 1,
-	HSA_DBG_WAVEMSG_ERROR = 2,
-	HSA_DBG_NUM_WAVEMSG,
-	HSA_DBG_MAX_WAVEMSG = 0xFFFFFFFF
-};
-
-enum HSA_DBG_WATCH_MODE {
-	HSA_DBG_WATCH_READ = 0,		/* Read operations only */
-	HSA_DBG_WATCH_NONREAD = 1,	/* Write or Atomic operations only */
-	HSA_DBG_WATCH_ATOMIC = 2,	/* Atomic Operations only */
-	HSA_DBG_WATCH_ALL = 3,		/* Read, Write or Atomic operations */
-	HSA_DBG_WATCH_NUM,
-	HSA_DBG_WATCH_SIZE = 0xFFFFFFFF
-};
-
-/* This structure is hardware specific and may change in the future */
-struct HsaDbgWaveMsgAMDGen2 {
-	union {
-		struct ui32 {
-			uint32_t UserData:8;	/* user data */
-			uint32_t ShaderArray:1;	/* Shader array */
-			uint32_t Priv:1;	/* Privileged */
-			uint32_t Reserved0:4;	/* Reserved, should be 0 */
-			uint32_t WaveId:4;	/* wave id */
-			uint32_t SIMD:2;	/* SIMD id */
-			uint32_t HSACU:4;	/* Compute unit */
-			uint32_t ShaderEngine:2;/* Shader engine */
-			uint32_t MessageType:2;	/* see HSA_DBG_WAVEMSG_TYPE */
-			uint32_t Reserved1:4;	/* Reserved, should be 0 */
-		} ui32;
-		uint32_t Value;
-	};
-	uint32_t Reserved2;
-};
-
-union HsaDbgWaveMessageAMD {
-	struct HsaDbgWaveMsgAMDGen2 WaveMsgInfoGen2;
-	/* for future HsaDbgWaveMsgAMDGen3; */
-};
-
-struct HsaDbgWaveMessage {
-	void *MemoryVA;		/* ptr to associated host-accessible data */
-	union HsaDbgWaveMessageAMD DbgWaveMsg;
-};
-
-/*
- * TODO: This definitions to be MOVED to kfd_event, once it is implemented.
- *
- * HSA sync primitive, Event and HW Exception notification API definitions.
- * The API functions allow the runtime to define a so-called sync-primitive,
- * a SW object combining a user-mode provided "syncvar" and a scheduler event
- * that can be signaled through a defined GPU interrupt. A syncvar is
- * a process virtual memory location of a certain size that can be accessed
- * by CPU and GPU shader code within the process to set and query the content
- * within that memory. The definition of the content is determined by the HSA
- * runtime and potentially GPU shader code interfacing with the HSA runtime.
- * The syncvar values may be commonly written through an PM4 WRITE_DATA packet
- * in the user mode instruction stream. The OS scheduler event is typically
- * associated and signaled by an interrupt issued by the GPU, but other HSA
- * system interrupt conditions from other HW (e.g. IOMMUv2) may be surfaced
- * by the KFD by this mechanism, too.
- */
-
-/* these are the new definitions for events */
-enum HSA_EVENTTYPE {
-	HSA_EVENTTYPE_SIGNAL = 0,	/* user-mode generated GPU signal */
-	HSA_EVENTTYPE_NODECHANGE = 1,	/* HSA node change (attach/detach) */
-	HSA_EVENTTYPE_DEVICESTATECHANGE = 2,	/* HSA device state change
-						 * (start/stop)
-						 */
-	HSA_EVENTTYPE_HW_EXCEPTION = 3,	/* GPU shader exception event */
-	HSA_EVENTTYPE_SYSTEM_EVENT = 4,	/* GPU SYSCALL with parameter info */
-	HSA_EVENTTYPE_DEBUG_EVENT = 5,	/* GPU signal for debugging */
-	HSA_EVENTTYPE_PROFILE_EVENT = 6,/* GPU signal for profiling */
-	HSA_EVENTTYPE_QUEUE_EVENT = 7,	/* GPU signal queue idle state
-					 * (EOP pm4)
-					 */
-	/* ...  */
-	HSA_EVENTTYPE_MAXID,
-	HSA_EVENTTYPE_TYPE_SIZE = 0xFFFFFFFF
-};
-
-/* Sub-definitions for various event types: Syncvar */
-struct HsaSyncVar {
-	union SyncVar {
-		void *UserData;	/* pointer to user mode data */
-		uint64_t UserDataPtrValue; /* 64bit compatibility of value */
-	} SyncVar;
-	uint64_t SyncVarSize;
-};
-
-/* Sub-definitions for various event types: NodeChange */
-
-enum HSA_EVENTTYPE_NODECHANGE_FLAGS {
-	HSA_EVENTTYPE_NODECHANGE_ADD = 0,
-	HSA_EVENTTYPE_NODECHANGE_REMOVE = 1,
-	HSA_EVENTTYPE_NODECHANGE_SIZE = 0xFFFFFFFF
-};
-
-struct HsaNodeChange {
-	/* HSA node added/removed on the platform */
-	enum HSA_EVENTTYPE_NODECHANGE_FLAGS Flags;
-};
-
-/* Sub-definitions for various event types: DeviceStateChange */
-enum HSA_EVENTTYPE_DEVICESTATECHANGE_FLAGS {
-	/* device started (and available) */
-	HSA_EVENTTYPE_DEVICESTATUSCHANGE_START = 0,
-	/* device stopped (i.e. unavailable) */
-	HSA_EVENTTYPE_DEVICESTATUSCHANGE_STOP = 1,
-	HSA_EVENTTYPE_DEVICESTATUSCHANGE_SIZE = 0xFFFFFFFF
-};
-
-enum HSA_DEVICE {
-	HSA_DEVICE_CPU = 0,
-	HSA_DEVICE_GPU = 1,
-	MAX_HSA_DEVICE = 2
-};
-
-struct HsaDeviceStateChange {
-	uint32_t NodeId;	/* F-NUMA node that contains the device */
-	enum HSA_DEVICE Device;	/* device type: GPU or CPU */
-	enum HSA_EVENTTYPE_DEVICESTATECHANGE_FLAGS Flags; /* event flags */
-};
-
-struct HsaEventData {
-	enum HSA_EVENTTYPE EventType; /* event type */
-	union EventData {
-		/*
-		 * return data associated with HSA_EVENTTYPE_SIGNAL
-		 * and other events
-		 */
-		struct HsaSyncVar SyncVar;
-
-		/* data associated with HSA_EVENTTYPE_NODE_CHANGE */
-		struct HsaNodeChange NodeChangeState;
-
-		/* data associated with HSA_EVENTTYPE_DEVICE_STATE_CHANGE */
-		struct HsaDeviceStateChange DeviceState;
-	} EventData;
-
-	/* the following data entries are internal to the KFD & thunk itself */
-
-	/* internal thunk store for Event data (OsEventHandle) */
-	uint64_t HWData1;
-	/* internal thunk store for Event data (HWAddress) */
-	uint64_t HWData2;
-	/* internal thunk store for Event data (HWData) */
-	uint32_t HWData3;
-};
-
-struct HsaEventDescriptor {
-	/* event type to allocate */
-	enum HSA_EVENTTYPE EventType;
-	/* H-NUMA node containing GPU device that is event source */
-	uint32_t NodeId;
-	/* pointer to user mode syncvar data, syncvar->UserDataPtrValue
-	 * may be NULL
-	 */
-	struct HsaSyncVar SyncVar;
-};
-
-struct HsaEvent {
-	uint32_t EventId;
-	struct HsaEventData EventData;
-};
-
-#pragma pack(pop)
-
-enum DBGDEV_TYPE {
-	DBGDEV_TYPE_ILLEGAL = 0,
-	DBGDEV_TYPE_NODIQ = 1,
-	DBGDEV_TYPE_DIQ = 2,
-	DBGDEV_TYPE_TEST = 3
-};
-
-struct dbg_address_watch_info {
-	struct kfd_process *process;
-	enum HSA_DBG_WATCH_MODE *watch_mode;
-	uint64_t *watch_address;
-	uint64_t *watch_mask;
-	struct HsaEvent *watch_event;
-	uint32_t num_watch_points;
-};
-
-struct dbg_wave_control_info {
-	struct kfd_process *process;
-	uint32_t trapId;
-	enum HSA_DBG_WAVEOP operand;
-	enum HSA_DBG_WAVEMODE mode;
-	struct HsaDbgWaveMessage dbgWave_msg;
-};
-
-struct kfd_dbgdev {
-
-	/* The device that owns this data. */
-	struct kfd_dev *dev;
-
-	/* kernel queue for DIQ */
-	struct kernel_queue *kq;
-
-	/* a pointer to the pqm of the calling process */
-	struct process_queue_manager *pqm;
-
-	/* type of debug device ( DIQ, non DIQ, etc. ) */
-	enum DBGDEV_TYPE type;
-
-	/* virtualized function pointers to device dbg */
-	int (*dbgdev_register)(struct kfd_dbgdev *dbgdev);
-	int (*dbgdev_unregister)(struct kfd_dbgdev *dbgdev);
-	int (*dbgdev_address_watch)(struct kfd_dbgdev *dbgdev,
-				struct dbg_address_watch_info *adw_info);
-	int (*dbgdev_wave_control)(struct kfd_dbgdev *dbgdev,
-				struct dbg_wave_control_info *wac_info);
-
-};
-
-struct kfd_dbgmgr {
-	u32 pasid;
-	struct kfd_dev *dev;
-	struct kfd_dbgdev *dbgdev;
-};
-
-/* prototypes for debug manager functions */
-struct mutex *kfd_get_dbgmgr_mutex(void);
-void kfd_dbgmgr_destroy(struct kfd_dbgmgr *pmgr);
-bool kfd_dbgmgr_create(struct kfd_dbgmgr **ppmgr, struct kfd_dev *pdev);
-long kfd_dbgmgr_register(struct kfd_dbgmgr *pmgr, struct kfd_process *p);
-long kfd_dbgmgr_unregister(struct kfd_dbgmgr *pmgr, struct kfd_process *p);
-long kfd_dbgmgr_wave_control(struct kfd_dbgmgr *pmgr,
-				struct dbg_wave_control_info *wac_info);
-long kfd_dbgmgr_address_watch(struct kfd_dbgmgr *pmgr,
-			struct dbg_address_watch_info *adw_info);
-#endif /* KFD_DBGMGR_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 2b65d0acae2c..7f1746289989 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -64,34 +64,33 @@ static void kfd_device_info_set_sdma_queue_num(struct kfd_dev *kfd)
 	uint32_t sdma_version = kfd->adev->ip_versions[SDMA0_HWIP][0];
 
 	switch (sdma_version) {
-		case IP_VERSION(4, 0, 0):/* VEGA10 */
-		case IP_VERSION(4, 0, 1):/* VEGA12 */
-		case IP_VERSION(4, 1, 0):/* RAVEN */
-		case IP_VERSION(4, 1, 1):/* RAVEN */
-		case IP_VERSION(4, 1, 2):/* RENOIR */
-		case IP_VERSION(5, 2, 1):/* VANGOGH */
-		case IP_VERSION(5, 2, 3):/* YELLOW_CARP */
-			kfd->device_info.num_sdma_queues_per_engine = 2;
-			break;
-		case IP_VERSION(4, 2, 0):/* VEGA20 */
-		case IP_VERSION(4, 2, 2):/* ARCTURUS */
-		case IP_VERSION(4, 4, 0):/* ALDEBARAN */
-		case IP_VERSION(5, 0, 0):/* NAVI10 */
-		case IP_VERSION(5, 0, 1):/* CYAN_SKILLFISH */
-		case IP_VERSION(5, 0, 2):/* NAVI14 */
-		case IP_VERSION(5, 0, 5):/* NAVI12 */
-		case IP_VERSION(5, 2, 0):/* SIENNA_CICHLID */
-		case IP_VERSION(5, 2, 2):/* NAVY_FLOUNDER */
-		case IP_VERSION(5, 2, 4):/* DIMGREY_CAVEFISH */
-		case IP_VERSION(5, 2, 5):/* BEIGE_GOBY */
-			kfd->device_info.num_sdma_queues_per_engine = 8;
-			break;
-		default:
-			dev_warn(kfd_device,
-				"Default sdma queue per engine(8) is set due to "
-				"mismatch of sdma ip block(SDMA_HWIP:0x%x).\n",
-                                sdma_version);
-			kfd->device_info.num_sdma_queues_per_engine = 8;
+	case IP_VERSION(4, 0, 0):/* VEGA10 */
+	case IP_VERSION(4, 0, 1):/* VEGA12 */
+	case IP_VERSION(4, 1, 0):/* RAVEN */
+	case IP_VERSION(4, 1, 1):/* RAVEN */
+	case IP_VERSION(4, 1, 2):/* RENOIR */
+	case IP_VERSION(5, 2, 1):/* VANGOGH */
+	case IP_VERSION(5, 2, 3):/* YELLOW_CARP */
+		kfd->device_info.num_sdma_queues_per_engine = 2;
+		break;
+	case IP_VERSION(4, 2, 0):/* VEGA20 */
+	case IP_VERSION(4, 2, 2):/* ARCTURUS */
+	case IP_VERSION(4, 4, 0):/* ALDEBARAN */
+	case IP_VERSION(5, 0, 0):/* NAVI10 */
+	case IP_VERSION(5, 0, 1):/* CYAN_SKILLFISH */
+	case IP_VERSION(5, 0, 2):/* NAVI14 */
+	case IP_VERSION(5, 0, 5):/* NAVI12 */
+	case IP_VERSION(5, 2, 0):/* SIENNA_CICHLID */
+	case IP_VERSION(5, 2, 2):/* NAVY_FLOUNDER */
+	case IP_VERSION(5, 2, 4):/* DIMGREY_CAVEFISH */
+	case IP_VERSION(5, 2, 5):/* BEIGE_GOBY */
+		kfd->device_info.num_sdma_queues_per_engine = 8;
+		break;
+	default:
+		dev_warn(kfd_device,
+			"Default sdma queue per engine(8) is set due to mismatch of sdma ip block(SDMA_HWIP:0x%x).\n",
+			sdma_version);
+		kfd->device_info.num_sdma_queues_per_engine = 8;
 	}
 }
 
@@ -111,6 +110,7 @@ static void kfd_device_info_set_event_interrupt_class(struct kfd_dev *kfd)
 	case IP_VERSION(10, 3, 1): /* VANGOGH */
 	case IP_VERSION(10, 3, 3): /* YELLOW_CARP */
 	case IP_VERSION(10, 1, 3): /* CYAN_SKILLFISH */
+	case IP_VERSION(10, 1, 4):
 	case IP_VERSION(10, 1, 10): /* NAVI10 */
 	case IP_VERSION(10, 1, 2): /* NAVI12 */
 	case IP_VERSION(10, 1, 1): /* NAVI14 */
@@ -308,6 +308,7 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 			break;
 		/* Cyan Skillfish */
 		case IP_VERSION(10, 1, 3):
+		case IP_VERSION(10, 1, 4):
 			gfx_target_version = 100103;
 			if (!vf)
 				f2g = &gfx_v10_kfd2kgd;
@@ -576,8 +577,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	if (kfd_resume(kfd))
 		goto kfd_resume_error;
 
-	kfd->dbgmgr = NULL;
-
 	if (kfd_topology_add_device(kfd)) {
 		dev_err(kfd_device, "Error adding device to topology\n");
 		goto kfd_topology_add_device_error;
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 4b6814949aad..7f6f1a842b0b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -58,7 +58,7 @@ static inline void deallocate_hqd(struct device_queue_manager *dqm,
 				struct queue *q);
 static int allocate_hqd(struct device_queue_manager *dqm, struct queue *q);
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
-				struct queue *q);
+				struct queue *q, const uint32_t *restore_sdma_id);
 static void kfd_process_hw_exception(struct work_struct *work);
 
 static inline
@@ -144,7 +144,13 @@ static void decrement_queue_count(struct device_queue_manager *dqm,
 		dqm->active_cp_queue_count--;
 }
 
-static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
+/*
+ * Allocate a doorbell ID to this queue.
+ * If doorbell_id is passed in, make sure requested ID is valid then allocate it.
+ */
+static int allocate_doorbell(struct qcm_process_device *qpd,
+			     struct queue *q,
+			     uint32_t const *restore_id)
 {
 	struct kfd_dev *dev = qpd->dqm->dev;
 
@@ -152,6 +158,10 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		/* On pre-SOC15 chips we need to use the queue ID to
 		 * preserve the user mode ABI.
 		 */
+
+		if (restore_id && *restore_id != q->properties.queue_id)
+			return -EINVAL;
+
 		q->doorbell_id = q->properties.queue_id;
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 			q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
@@ -160,25 +170,37 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		 * The doobell index distance between RLC (2*i) and (2*i+1)
 		 * for a SDMA engine is 512.
 		 */
-		uint32_t *idx_offset =
-				dev->shared_resources.sdma_doorbell_idx;
 
-		q->doorbell_id = idx_offset[q->properties.sdma_engine_id]
-			+ (q->properties.sdma_queue_id & 1)
-			* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
-			+ (q->properties.sdma_queue_id >> 1);
+		uint32_t *idx_offset = dev->shared_resources.sdma_doorbell_idx;
+		uint32_t valid_id = idx_offset[q->properties.sdma_engine_id]
+						+ (q->properties.sdma_queue_id & 1)
+						* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
+						+ (q->properties.sdma_queue_id >> 1);
+
+		if (restore_id && *restore_id != valid_id)
+			return -EINVAL;
+		q->doorbell_id = valid_id;
 	} else {
-		/* For CP queues on SOC15 reserve a free doorbell ID */
-		unsigned int found;
-
-		found = find_first_zero_bit(qpd->doorbell_bitmap,
-					    KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
-		if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
-			pr_debug("No doorbells available");
-			return -EBUSY;
+		/* For CP queues on SOC15 */
+		if (restore_id) {
+			/* make sure that ID is free  */
+			if (__test_and_set_bit(*restore_id, qpd->doorbell_bitmap))
+				return -EINVAL;
+
+			q->doorbell_id = *restore_id;
+		} else {
+			/* or reserve a free doorbell ID */
+			unsigned int found;
+
+			found = find_first_zero_bit(qpd->doorbell_bitmap,
+						KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
+			if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
+				pr_debug("No doorbells available");
+				return -EBUSY;
+			}
+			set_bit(found, qpd->doorbell_bitmap);
+			q->doorbell_id = found;
 		}
-		set_bit(found, qpd->doorbell_bitmap);
-		q->doorbell_id = found;
 	}
 
 	q->properties.doorbell_off =
@@ -299,7 +321,9 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 
 static int create_queue_nocpsch(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd)
+				struct qcm_process_device *qpd,
+				const struct kfd_criu_queue_priv_data *qd,
+				const void *restore_mqd, const void *restore_ctl_stack)
 {
 	struct mqd_manager *mqd_mgr;
 	int retval;
@@ -339,13 +363,13 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			q->pipe, q->queue);
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
-		retval = allocate_sdma_queue(dqm, q);
+		retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
 		if (retval)
 			goto deallocate_vmid;
 		dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
 	}
 
-	retval = allocate_doorbell(qpd, q);
+	retval = allocate_doorbell(qpd, q, qd ? &qd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_hqd;
 
@@ -358,8 +382,15 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 		retval = -ENOMEM;
 		goto out_deallocate_doorbell;
 	}
-	mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
-				&q->gart_mqd_addr, &q->properties);
+
+	if (qd)
+		mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,
+				     &q->properties, restore_mqd, restore_ctl_stack,
+				     qd->ctl_stack_size);
+	else
+		mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
+					&q->gart_mqd_addr, &q->properties);
+
 	if (q->properties.is_active) {
 		if (!dqm->sched_running) {
 			WARN_ONCE(1, "Load non-HWS mqd while stopped\n");
@@ -449,6 +480,65 @@ static inline void deallocate_hqd(struct device_queue_manager *dqm,
 	dqm->allocated_queues[q->pipe] |= (1 << q->queue);
 }
 
+#define SQ_IND_CMD_CMD_KILL		0x00000003
+#define SQ_IND_CMD_MODE_BROADCAST	0x00000001
+
+static int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
+{
+	int status = 0;
+	unsigned int vmid;
+	uint16_t queried_pasid;
+	union SQ_CMD_BITS reg_sq_cmd;
+	union GRBM_GFX_INDEX_BITS reg_gfx_index;
+	struct kfd_process_device *pdd;
+	int first_vmid_to_scan = dev->vm_info.first_vmid_kfd;
+	int last_vmid_to_scan = dev->vm_info.last_vmid_kfd;
+
+	reg_sq_cmd.u32All = 0;
+	reg_gfx_index.u32All = 0;
+
+	pr_debug("Killing all process wavefronts\n");
+
+	/* Scan all registers in the range ATC_VMID8_PASID_MAPPING ..
+	 * ATC_VMID15_PASID_MAPPING
+	 * to check which VMID the current process is mapped to.
+	 */
+
+	for (vmid = first_vmid_to_scan; vmid <= last_vmid_to_scan; vmid++) {
+		status = dev->kfd2kgd->get_atc_vmid_pasid_mapping_info
+				(dev->adev, vmid, &queried_pasid);
+
+		if (status && queried_pasid == p->pasid) {
+			pr_debug("Killing wave fronts of vmid %d and pasid 0x%x\n",
+					vmid, p->pasid);
+			break;
+		}
+	}
+
+	if (vmid > last_vmid_to_scan) {
+		pr_err("Didn't find vmid for pasid 0x%x\n", p->pasid);
+		return -EFAULT;
+	}
+
+	/* taking the VMID for that process on the safe way using PDD */
+	pdd = kfd_get_process_device_data(dev, p);
+	if (!pdd)
+		return -EFAULT;
+
+	reg_gfx_index.bits.sh_broadcast_writes = 1;
+	reg_gfx_index.bits.se_broadcast_writes = 1;
+	reg_gfx_index.bits.instance_broadcast_writes = 1;
+	reg_sq_cmd.bits.mode = SQ_IND_CMD_MODE_BROADCAST;
+	reg_sq_cmd.bits.cmd = SQ_IND_CMD_CMD_KILL;
+	reg_sq_cmd.bits.vm_id = vmid;
+
+	dev->kfd2kgd->wave_control_execute(dev->adev,
+					reg_gfx_index.u32All,
+					reg_sq_cmd.u32All);
+
+	return 0;
+}
+
 /* Access to DQM has to be locked before calling destroy_queue_nocpsch_locked
  * to avoid asynchronized access
  */
@@ -1034,7 +1124,7 @@ static void pre_reset(struct device_queue_manager *dqm)
 }
 
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
-				struct queue *q)
+				struct queue *q, const uint32_t *restore_sdma_id)
 {
 	int bit;
 
@@ -1044,9 +1134,21 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 			return -ENOMEM;
 		}
 
-		bit = __ffs64(dqm->sdma_bitmap);
-		dqm->sdma_bitmap &= ~(1ULL << bit);
-		q->sdma_id = bit;
+		if (restore_sdma_id) {
+			/* Re-use existing sdma_id */
+			if (!(dqm->sdma_bitmap & (1ULL << *restore_sdma_id))) {
+				pr_err("SDMA queue already in use\n");
+				return -EBUSY;
+			}
+			dqm->sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+			q->sdma_id = *restore_sdma_id;
+		} else {
+			/* Find first available sdma_id */
+			bit = __ffs64(dqm->sdma_bitmap);
+			dqm->sdma_bitmap &= ~(1ULL << bit);
+			q->sdma_id = bit;
+		}
+
 		q->properties.sdma_engine_id = q->sdma_id %
 				kfd_get_num_sdma_engines(dqm->dev);
 		q->properties.sdma_queue_id = q->sdma_id /
@@ -1056,9 +1158,19 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 			pr_err("No more XGMI SDMA queue to allocate\n");
 			return -ENOMEM;
 		}
-		bit = __ffs64(dqm->xgmi_sdma_bitmap);
-		dqm->xgmi_sdma_bitmap &= ~(1ULL << bit);
-		q->sdma_id = bit;
+		if (restore_sdma_id) {
+			/* Re-use existing sdma_id */
+			if (!(dqm->xgmi_sdma_bitmap & (1ULL << *restore_sdma_id))) {
+				pr_err("SDMA queue already in use\n");
+				return -EBUSY;
+			}
+			dqm->xgmi_sdma_bitmap &= ~(1ULL << *restore_sdma_id);
+			q->sdma_id = *restore_sdma_id;
+		} else {
+			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
@@ -1288,7 +1400,9 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
-			struct qcm_process_device *qpd)
+			struct qcm_process_device *qpd,
+			const struct kfd_criu_queue_priv_data *qd,
+			const void *restore_mqd, const void *restore_ctl_stack)
 {
 	int retval;
 	struct mqd_manager *mqd_mgr;
@@ -1303,13 +1417,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 		q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
 		dqm_lock(dqm);
-		retval = allocate_sdma_queue(dqm, q);
+		retval = allocate_sdma_queue(dqm, q, qd ? &qd->sdma_id : NULL);
 		dqm_unlock(dqm);
 		if (retval)
 			goto out;
 	}
 
-	retval = allocate_doorbell(qpd, q);
+	retval = allocate_doorbell(qpd, q, qd ? &qd->doorbell_id : NULL);
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
@@ -1334,8 +1448,14 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	 * updates the is_evicted flag but is a no-op otherwise.
 	 */
 	q->properties.is_evicted = !!qpd->evicted;
-	mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
-				&q->gart_mqd_addr, &q->properties);
+
+	if (qd)
+		mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,
+				     &q->properties, restore_mqd, restore_ctl_stack,
+				     qd->ctl_stack_size);
+	else
+		mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
+					&q->gart_mqd_addr, &q->properties);
 
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
@@ -1738,6 +1858,56 @@ static int get_wave_state(struct device_queue_manager *dqm,
 			ctl_stack_used_size, save_area_used_size);
 }
 
+static void get_queue_checkpoint_info(struct device_queue_manager *dqm,
+			const struct queue *q,
+			u32 *mqd_size,
+			u32 *ctl_stack_size)
+{
+	struct mqd_manager *mqd_mgr;
+	enum KFD_MQD_TYPE mqd_type =
+			get_mqd_type_from_queue_type(q->properties.type);
+
+	dqm_lock(dqm);
+	mqd_mgr = dqm->mqd_mgrs[mqd_type];
+	*mqd_size = mqd_mgr->mqd_size;
+	*ctl_stack_size = 0;
+
+	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE && mqd_mgr->get_checkpoint_info)
+		mqd_mgr->get_checkpoint_info(mqd_mgr, q->mqd, ctl_stack_size);
+
+	dqm_unlock(dqm);
+}
+
+static int checkpoint_mqd(struct device_queue_manager *dqm,
+			  const struct queue *q,
+			  void *mqd,
+			  void *ctl_stack)
+{
+	struct mqd_manager *mqd_mgr;
+	int r = 0;
+	enum KFD_MQD_TYPE mqd_type =
+			get_mqd_type_from_queue_type(q->properties.type);
+
+	dqm_lock(dqm);
+
+	if (q->properties.is_active || !q->device->cwsr_enabled) {
+		r = -EINVAL;
+		goto dqm_unlock;
+	}
+
+	mqd_mgr = dqm->mqd_mgrs[mqd_type];
+	if (!mqd_mgr->checkpoint_mqd) {
+		r = -EOPNOTSUPP;
+		goto dqm_unlock;
+	}
+
+	mqd_mgr->checkpoint_mqd(mqd_mgr, q->mqd, mqd, ctl_stack);
+
+dqm_unlock:
+	dqm_unlock(dqm);
+	return r;
+}
+
 static int process_termination_cpsch(struct device_queue_manager *dqm,
 		struct qcm_process_device *qpd)
 {
@@ -1915,6 +2085,8 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.restore_process_queues = restore_process_queues_cpsch;
 		dqm->ops.get_wave_state = get_wave_state;
 		dqm->ops.reset_queues = reset_queues_cpsch;
+		dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info;
+		dqm->ops.checkpoint_mqd = checkpoint_mqd;
 		break;
 	case KFD_SCHED_POLICY_NO_HWS:
 		/* initialize dqm for no cp scheduling */
@@ -1934,6 +2106,8 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.restore_process_queues =
 			restore_process_queues_nocpsch;
 		dqm->ops.get_wave_state = get_wave_state;
+		dqm->ops.get_queue_checkpoint_info = get_queue_checkpoint_info;
+		dqm->ops.checkpoint_mqd = checkpoint_mqd;
 		break;
 	default:
 		pr_err("Invalid scheduling policy %d\n", dqm->sched_policy);
@@ -2005,7 +2179,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
-int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid)
+int kfd_dqm_evict_pasid(struct device_queue_manager *dqm, u32 pasid)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
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 e145e4deb53a..05a9c17daa3e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -39,6 +39,41 @@ struct device_process_node {
 	struct list_head list;
 };
 
+union SQ_CMD_BITS {
+	struct {
+		uint32_t cmd:3;
+		uint32_t:1;
+		uint32_t mode:3;
+		uint32_t check_vmid:1;
+		uint32_t trap_id:3;
+		uint32_t:5;
+		uint32_t wave_id:4;
+		uint32_t simd_id:2;
+		uint32_t:2;
+		uint32_t queue_id:3;
+		uint32_t:1;
+		uint32_t vm_id:4;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
+union GRBM_GFX_INDEX_BITS {
+	struct {
+		uint32_t instance_index:8;
+		uint32_t sh_index:8;
+		uint32_t se_index:8;
+		uint32_t:5;
+		uint32_t sh_broadcast_writes:1;
+		uint32_t instance_broadcast_writes:1;
+		uint32_t se_broadcast_writes:1;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
 /**
  * struct device_queue_manager_ops
  *
@@ -83,12 +118,18 @@ struct device_process_node {
  * control stack, if kept in the MQD, to the given userspace address.
  *
  * @reset_queues: reset queues which consume RAS poison
+ * @get_queue_checkpoint_info: Retrieves queue size information for CRIU checkpoint.
+ *
+ * @checkpoint_mqd: checkpoint queue MQD contents for CRIU.
  */
 
 struct device_queue_manager_ops {
 	int	(*create_queue)(struct device_queue_manager *dqm,
 				struct queue *q,
-				struct qcm_process_device *qpd);
+				struct qcm_process_device *qpd,
+				const struct kfd_criu_queue_priv_data *qd,
+				const void *restore_mqd,
+				const void *restore_ctl_stack);
 
 	int	(*destroy_queue)(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
@@ -139,6 +180,14 @@ struct device_queue_manager_ops {
 
 	int (*reset_queues)(struct device_queue_manager *dqm,
 					uint16_t pasid);
+	void	(*get_queue_checkpoint_info)(struct device_queue_manager *dqm,
+				  const struct queue *q, u32 *mqd_size,
+				  u32 *ctl_stack_size);
+
+	int	(*checkpoint_mqd)(struct device_queue_manager *dqm,
+				  const struct queue *q,
+				  void *mqd,
+				  void *ctl_stack);
 };
 
 struct device_queue_manager_asic_ops {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index afe72dd11325..b5eda1e04f34 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -55,7 +55,6 @@ struct kfd_signal_page {
 	bool need_to_free_pages;
 };
 
-
 static uint64_t *page_slots(struct kfd_signal_page *page)
 {
 	return page->kernel_address;
@@ -92,7 +91,8 @@ fail_alloc_signal_store:
 }
 
 static int allocate_event_notification_slot(struct kfd_process *p,
-					    struct kfd_event *ev)
+					    struct kfd_event *ev,
+					    const int *restore_id)
 {
 	int id;
 
@@ -104,14 +104,19 @@ static int allocate_event_notification_slot(struct kfd_process *p,
 		p->signal_mapped_size = 256*8;
 	}
 
-	/*
-	 * Compatibility with old user mode: Only use signal slots
-	 * user mode has mapped, may be less than
-	 * KFD_SIGNAL_EVENT_LIMIT. This also allows future increase
-	 * of the event limit without breaking user mode.
-	 */
-	id = idr_alloc(&p->event_idr, ev, 0, p->signal_mapped_size / 8,
-		       GFP_KERNEL);
+	if (restore_id) {
+		id = idr_alloc(&p->event_idr, ev, *restore_id, *restore_id + 1,
+				GFP_KERNEL);
+	} else {
+		/*
+		 * Compatibility with old user mode: Only use signal slots
+		 * user mode has mapped, may be less than
+		 * KFD_SIGNAL_EVENT_LIMIT. This also allows future increase
+		 * of the event limit without breaking user mode.
+		 */
+		id = idr_alloc(&p->event_idr, ev, 0, p->signal_mapped_size / 8,
+				GFP_KERNEL);
+	}
 	if (id < 0)
 		return id;
 
@@ -178,9 +183,8 @@ static struct kfd_event *lookup_signaled_event_by_partial_id(
 	return ev;
 }
 
-static int create_signal_event(struct file *devkfd,
-				struct kfd_process *p,
-				struct kfd_event *ev)
+static int create_signal_event(struct file *devkfd, struct kfd_process *p,
+				struct kfd_event *ev, const int *restore_id)
 {
 	int ret;
 
@@ -193,7 +197,7 @@ static int create_signal_event(struct file *devkfd,
 		return -ENOSPC;
 	}
 
-	ret = allocate_event_notification_slot(p, ev);
+	ret = allocate_event_notification_slot(p, ev, restore_id);
 	if (ret) {
 		pr_warn("Signal event wasn't created because out of kernel memory\n");
 		return ret;
@@ -209,16 +213,22 @@ static int create_signal_event(struct file *devkfd,
 	return 0;
 }
 
-static int create_other_event(struct kfd_process *p, struct kfd_event *ev)
+static int create_other_event(struct kfd_process *p, struct kfd_event *ev, const int *restore_id)
 {
-	/* Cast KFD_LAST_NONSIGNAL_EVENT to uint32_t. This allows an
-	 * intentional integer overflow to -1 without a compiler
-	 * warning. idr_alloc treats a negative value as "maximum
-	 * signed integer".
-	 */
-	int id = idr_alloc(&p->event_idr, ev, KFD_FIRST_NONSIGNAL_EVENT_ID,
-			   (uint32_t)KFD_LAST_NONSIGNAL_EVENT_ID + 1,
-			   GFP_KERNEL);
+	int id;
+
+	if (restore_id)
+		id = idr_alloc(&p->event_idr, ev, *restore_id, *restore_id + 1,
+			GFP_KERNEL);
+	else
+		/* Cast KFD_LAST_NONSIGNAL_EVENT to uint32_t. This allows an
+		 * intentional integer overflow to -1 without a compiler
+		 * warning. idr_alloc treats a negative value as "maximum
+		 * signed integer".
+		 */
+		id = idr_alloc(&p->event_idr, ev, KFD_FIRST_NONSIGNAL_EVENT_ID,
+				(uint32_t)KFD_LAST_NONSIGNAL_EVENT_ID + 1,
+				GFP_KERNEL);
 
 	if (id < 0)
 		return id;
@@ -295,8 +305,8 @@ static bool event_can_be_cpu_signaled(const struct kfd_event *ev)
 	return ev->type == KFD_EVENT_TYPE_SIGNAL;
 }
 
-int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
-		       uint64_t size)
+static int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
+		       uint64_t size, uint64_t user_handle)
 {
 	struct kfd_signal_page *page;
 
@@ -315,10 +325,57 @@ int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
 
 	p->signal_page = page;
 	p->signal_mapped_size = size;
-
+	p->signal_handle = user_handle;
 	return 0;
 }
 
+int kfd_kmap_event_page(struct kfd_process *p, uint64_t event_page_offset)
+{
+	struct kfd_dev *kfd;
+	struct kfd_process_device *pdd;
+	void *mem, *kern_addr;
+	uint64_t size;
+	int err = 0;
+
+	if (p->signal_page) {
+		pr_err("Event page is already set\n");
+		return -EINVAL;
+	}
+
+	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))
+		return PTR_ERR(pdd);
+
+	mem = kfd_process_device_translate_handle(pdd,
+			GET_IDR_HANDLE(event_page_offset));
+	if (!mem) {
+		pr_err("Can't find BO, offset is 0x%llx\n", event_page_offset);
+		return -EINVAL;
+	}
+
+	err = amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(kfd->adev,
+					mem, &kern_addr, &size);
+	if (err) {
+		pr_err("Failed to map event page to kernel\n");
+		return err;
+	}
+
+	err = kfd_event_page_set(p, kern_addr, size, event_page_offset);
+	if (err) {
+		pr_err("Failed to set event page\n");
+		amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(kfd->adev, mem);
+		return err;
+	}
+	return err;
+}
+
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,
@@ -343,14 +400,14 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 	switch (event_type) {
 	case KFD_EVENT_TYPE_SIGNAL:
 	case KFD_EVENT_TYPE_DEBUG:
-		ret = create_signal_event(devkfd, p, ev);
+		ret = create_signal_event(devkfd, p, ev, NULL);
 		if (!ret) {
 			*event_page_offset = KFD_MMAP_TYPE_EVENTS;
 			*event_slot_index = ev->event_id;
 		}
 		break;
 	default:
-		ret = create_other_event(p, ev);
+		ret = create_other_event(p, ev, NULL);
 		break;
 	}
 
@@ -366,6 +423,166 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 	return ret;
 }
 
+int kfd_criu_restore_event(struct file *devkfd,
+			   struct kfd_process *p,
+			   uint8_t __user *user_priv_ptr,
+			   uint64_t *priv_data_offset,
+			   uint64_t max_priv_data_size)
+{
+	struct kfd_criu_event_priv_data *ev_priv;
+	struct kfd_event *ev = NULL;
+	int ret = 0;
+
+	ev_priv = kmalloc(sizeof(*ev_priv), GFP_KERNEL);
+	if (!ev_priv)
+		return -ENOMEM;
+
+	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
+	if (!ev) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	if (*priv_data_offset + sizeof(*ev_priv) > max_priv_data_size) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	ret = copy_from_user(ev_priv, user_priv_ptr + *priv_data_offset, sizeof(*ev_priv));
+	if (ret) {
+		ret = -EFAULT;
+		goto exit;
+	}
+	*priv_data_offset += sizeof(*ev_priv);
+
+	if (ev_priv->user_handle) {
+		ret = kfd_kmap_event_page(p, ev_priv->user_handle);
+		if (ret)
+			goto exit;
+	}
+
+	ev->type = ev_priv->type;
+	ev->auto_reset = ev_priv->auto_reset;
+	ev->signaled = ev_priv->signaled;
+
+	init_waitqueue_head(&ev->wq);
+
+	mutex_lock(&p->event_mutex);
+	switch (ev->type) {
+	case KFD_EVENT_TYPE_SIGNAL:
+	case KFD_EVENT_TYPE_DEBUG:
+		ret = create_signal_event(devkfd, p, ev, &ev_priv->event_id);
+		break;
+	case KFD_EVENT_TYPE_MEMORY:
+		memcpy(&ev->memory_exception_data,
+			&ev_priv->memory_exception_data,
+			sizeof(struct kfd_hsa_memory_exception_data));
+
+		ret = create_other_event(p, ev, &ev_priv->event_id);
+		break;
+	case KFD_EVENT_TYPE_HW_EXCEPTION:
+		memcpy(&ev->hw_exception_data,
+			&ev_priv->hw_exception_data,
+			sizeof(struct kfd_hsa_hw_exception_data));
+
+		ret = create_other_event(p, ev, &ev_priv->event_id);
+		break;
+	}
+
+exit:
+	if (ret)
+		kfree(ev);
+
+	kfree(ev_priv);
+
+	mutex_unlock(&p->event_mutex);
+
+	return ret;
+}
+
+int kfd_criu_checkpoint_events(struct kfd_process *p,
+			 uint8_t __user *user_priv_data,
+			 uint64_t *priv_data_offset)
+{
+	struct kfd_criu_event_priv_data *ev_privs;
+	int i = 0;
+	int ret =  0;
+	struct kfd_event *ev;
+	uint32_t ev_id;
+
+	uint32_t num_events = kfd_get_num_events(p);
+
+	if (!num_events)
+		return 0;
+
+	ev_privs = kvzalloc(num_events * sizeof(*ev_privs), GFP_KERNEL);
+	if (!ev_privs)
+		return -ENOMEM;
+
+
+	idr_for_each_entry(&p->event_idr, ev, ev_id) {
+		struct kfd_criu_event_priv_data *ev_priv;
+
+		/*
+		 * Currently, all events have same size of private_data, but the current ioctl's
+		 * and CRIU plugin supports private_data of variable sizes
+		 */
+		ev_priv = &ev_privs[i];
+
+		ev_priv->object_type = KFD_CRIU_OBJECT_TYPE_EVENT;
+
+		/* We store the user_handle with the first event */
+		if (i == 0 && p->signal_page)
+			ev_priv->user_handle = p->signal_handle;
+
+		ev_priv->event_id = ev->event_id;
+		ev_priv->auto_reset = ev->auto_reset;
+		ev_priv->type = ev->type;
+		ev_priv->signaled = ev->signaled;
+
+		if (ev_priv->type == KFD_EVENT_TYPE_MEMORY)
+			memcpy(&ev_priv->memory_exception_data,
+				&ev->memory_exception_data,
+				sizeof(struct kfd_hsa_memory_exception_data));
+		else if (ev_priv->type == KFD_EVENT_TYPE_HW_EXCEPTION)
+			memcpy(&ev_priv->hw_exception_data,
+				&ev->hw_exception_data,
+				sizeof(struct kfd_hsa_hw_exception_data));
+
+		pr_debug("Checkpointed event[%d] id = 0x%08x auto_reset = %x type = %x signaled = %x\n",
+			  i,
+			  ev_priv->event_id,
+			  ev_priv->auto_reset,
+			  ev_priv->type,
+			  ev_priv->signaled);
+		i++;
+	}
+
+	ret = copy_to_user(user_priv_data + *priv_data_offset,
+			   ev_privs, num_events * sizeof(*ev_privs));
+	if (ret) {
+		pr_err("Failed to copy events priv to user\n");
+		ret = -EFAULT;
+	}
+
+	*priv_data_offset += num_events * sizeof(*ev_privs);
+
+	kvfree(ev_privs);
+	return ret;
+}
+
+int kfd_get_num_events(struct kfd_process *p)
+{
+	struct kfd_event *ev;
+	uint32_t id;
+	u32 num_events = 0;
+
+	idr_for_each_entry(&p->event_idr, ev, id)
+		num_events++;
+
+	return num_events;
+}
+
 /* Assumes that p is current. */
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id)
 {
@@ -878,6 +1095,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
 {
 	struct kfd_hsa_memory_exception_data memory_exception_data;
 	struct vm_area_struct *vma;
+	int user_gpu_id;
 
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
@@ -899,12 +1117,17 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
 		return; /* Process is exiting */
 	}
 
+	user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
+	if (unlikely(user_gpu_id == -EINVAL)) {
+		WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id);
+		return;
+	}
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 
 	mmap_read_lock(mm);
 	vma = find_vma(mm, address);
 
-	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.gpu_id = user_gpu_id;
 	memory_exception_data.va = address;
 	/* Set failure reason */
 	memory_exception_data.failure.NotPresent = 1;
@@ -980,11 +1203,19 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 	uint32_t id;
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
 	struct kfd_hsa_memory_exception_data memory_exception_data;
+	int user_gpu_id;
 
 	if (!p)
 		return; /* Presumably process exited. */
+
+	user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
+	if (unlikely(user_gpu_id == -EINVAL)) {
+		WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id);
+		return;
+	}
+
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
-	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.gpu_id = user_gpu_id;
 	memory_exception_data.failure.imprecise = true;
 	/* Set failure reason */
 	if (info) {
@@ -1024,27 +1255,34 @@ void kfd_signal_reset_event(struct kfd_dev *dev)
 
 	/* Whole gpu reset caused by GPU hang and memory is lost */
 	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
-	hw_exception_data.gpu_id = dev->id;
 	hw_exception_data.memory_lost = 1;
 	hw_exception_data.reset_cause = reset_cause;
 
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 	memory_exception_data.ErrorType = KFD_MEM_ERR_SRAM_ECC;
-	memory_exception_data.gpu_id = dev->id;
 	memory_exception_data.failure.imprecise = true;
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		int user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
+
+		if (unlikely(user_gpu_id == -EINVAL)) {
+			WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id);
+			continue;
+		}
+
 		mutex_lock(&p->event_mutex);
 		id = KFD_FIRST_NONSIGNAL_EVENT_ID;
 		idr_for_each_entry_continue(&p->event_idr, ev, id) {
 			if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
 				ev->hw_exception_data = hw_exception_data;
+				ev->hw_exception_data.gpu_id = user_gpu_id;
 				set_event(ev);
 			}
 			if (ev->type == KFD_EVENT_TYPE_MEMORY &&
 			    reset_cause == KFD_HW_EXCEPTION_ECC) {
 				ev->memory_exception_data = memory_exception_data;
+				ev->memory_exception_data.gpu_id = user_gpu_id;
 				set_event(ev);
 			}
 		}
@@ -1060,18 +1298,25 @@ void kfd_signal_poison_consumed_event(struct kfd_dev *dev, u32 pasid)
 	struct kfd_hsa_hw_exception_data hw_exception_data;
 	struct kfd_event *ev;
 	uint32_t id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+	int user_gpu_id;
 
 	if (!p)
 		return; /* Presumably process exited. */
 
+	user_gpu_id = kfd_process_get_user_gpu_id(p, dev->id);
+	if (unlikely(user_gpu_id == -EINVAL)) {
+		WARN_ONCE(1, "Could not get user_gpu_id from dev->id:%x\n", dev->id);
+		return;
+	}
+
 	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
-	hw_exception_data.gpu_id = dev->id;
+	hw_exception_data.gpu_id = user_gpu_id;
 	hw_exception_data.memory_lost = 1;
 	hw_exception_data.reset_cause = KFD_HW_EXCEPTION_ECC;
 
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 	memory_exception_data.ErrorType = KFD_MEM_ERR_POISON_CONSUMED;
-	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.gpu_id = user_gpu_id;
 	memory_exception_data.failure.imprecise = true;
 
 	mutex_lock(&p->event_mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index e8bc28009c22..68ee923a440b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -109,8 +109,7 @@ static void event_interrupt_poison_consumption(struct kfd_dev *dev,
 
 	switch (source_id) {
 	case SOC15_INTSRC_SQ_INTERRUPT_MSG:
-		if (dev->dqm->ops.reset_queues)
-			ret = dev->dqm->ops.reset_queues(dev->dqm, pasid);
+		kfd_dqm_evict_pasid(dev->dqm, pasid);
 		break;
 	case SOC15_INTSRC_SDMA_ECC:
 	default:
@@ -308,7 +307,7 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 		info.prot_write = ring_id & 0x20;
 
 		kfd_smi_event_update_vmfault(dev, pasid);
-		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_dqm_evict_pasid(dev->dqm, pasid);
 		kfd_signal_vm_fault_event(dev, pasid, &info);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 66ad8d0b8f7f..fe62407dacb2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -30,7 +30,6 @@
 #include <linux/pci.h>
 #include <linux/amd-iommu.h>
 #include "kfd_priv.h"
-#include "kfd_dbgmgr.h"
 #include "kfd_topology.h"
 #include "kfd_iommu.h"
 
@@ -163,17 +162,6 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 
 	pr_debug("Unbinding process 0x%x from IOMMU\n", pasid);
 
-	mutex_lock(kfd_get_dbgmgr_mutex());
-
-	if (dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) {
-		if (!kfd_dbgmgr_unregister(dev->dbgmgr, p)) {
-			kfd_dbgmgr_destroy(dev->dbgmgr);
-			dev->dbgmgr = NULL;
-		}
-	}
-
-	mutex_unlock(kfd_get_dbgmgr_mutex());
-
 	mutex_lock(&p->mutex);
 
 	pdd = kfd_get_process_device_data(dev, p);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index ed5385137f48..7dcafd337bb2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -36,7 +36,7 @@
 #ifdef dev_fmt
 #undef dev_fmt
 #endif
-#define dev_fmt(fmt) "kfd_migrate: %s: " fmt, __func__
+#define dev_fmt(fmt) "kfd_migrate: " fmt
 
 static uint64_t
 svm_migrate_direct_mapping_addr(struct amdgpu_device *adev, uint64_t addr)
@@ -86,10 +86,7 @@ svm_migrate_gart_map(struct amdgpu_ring *ring, uint64_t npages,
 
 	cpu_addr = &job->ibs[0].ptr[num_dw];
 
-	r = amdgpu_gart_map(adev, 0, npages, addr, pte_flags, cpu_addr);
-	if (r)
-		goto error_free;
-
+	amdgpu_gart_map(adev, 0, npages, addr, pte_flags, cpu_addr);
 	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
 	if (r)
@@ -315,7 +312,7 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	r = svm_range_vram_node_new(adev, prange, true);
 	if (r) {
-		dev_err(adev->dev, "fail %d to alloc vram\n", r);
+		dev_dbg(adev->dev, "fail %d to alloc vram\n", r);
 		goto out;
 	}
 
@@ -334,7 +331,8 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 					      DMA_TO_DEVICE);
 			r = dma_mapping_error(dev, src[i]);
 			if (r) {
-				dev_err(adev->dev, "fail %d dma_map_page\n", r);
+				dev_err(adev->dev, "%s: fail %d dma_map_page\n",
+					__func__, r);
 				goto out_free_vram_pages;
 			}
 		} else {
@@ -435,8 +433,8 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	r = migrate_vma_setup(&migrate);
 	if (r) {
-		dev_err(adev->dev, "vma setup fail %d range [0x%lx 0x%lx]\n", r,
-			prange->start, prange->last);
+		dev_err(adev->dev, "%s: vma setup fail %d range [0x%lx 0x%lx]\n",
+			__func__, r, prange->start, prange->last);
 		goto out_free;
 	}
 
@@ -614,7 +612,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_FROM_DEVICE);
 		r = dma_mapping_error(dev, dst[i]);
 		if (r) {
-			dev_err(adev->dev, "fail %d dma_map_page\n", r);
+			dev_err(adev->dev, "%s: fail %d dma_map_page\n", __func__, r);
 			goto out_oom;
 		}
 
@@ -674,8 +672,8 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	r = migrate_vma_setup(&migrate);
 	if (r) {
-		dev_err(adev->dev, "vma setup fail %d range [0x%lx 0x%lx]\n", r,
-			prange->start, prange->last);
+		dev_err(adev->dev, "%s: vma setup fail %d range [0x%lx 0x%lx]\n",
+			__func__, r, prange->start, prange->last);
 		goto out_free;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index e2825ad4d699..9b7544ddced7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -173,3 +173,66 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		}
 	}
 }
+
+int kfd_hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+		     uint32_t pipe_id, uint32_t queue_id,
+		     struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->adev, mqd, pipe_id,
+					      queue_id, p->doorbell_off);
+}
+
+int kfd_destroy_mqd_cp(struct mqd_manager *mm, void *mqd,
+		enum kfd_preempt_type type, unsigned int timeout,
+		uint32_t pipe_id, uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_destroy(mm->dev->adev, mqd, type, timeout,
+						pipe_id, queue_id);
+}
+
+void kfd_free_mqd_cp(struct mqd_manager *mm, void *mqd,
+	      struct kfd_mem_obj *mqd_mem_obj)
+{
+	if (mqd_mem_obj->gtt_mem) {
+		amdgpu_amdkfd_free_gtt_mem(mm->dev->adev, mqd_mem_obj->gtt_mem);
+		kfree(mqd_mem_obj);
+	} else {
+		kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
+	}
+}
+
+bool kfd_is_occupied_cp(struct mqd_manager *mm, void *mqd,
+		 uint64_t queue_address, uint32_t pipe_id,
+		 uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_is_occupied(mm->dev->adev, queue_address,
+						pipe_id, queue_id);
+}
+
+int kfd_load_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		  uint32_t pipe_id, uint32_t queue_id,
+		  struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd,
+						(uint32_t __user *)p->write_ptr,
+						mms);
+}
+
+/*
+ * preempt type here is ignored because there is only one way
+ * to preempt sdma queue
+ */
+int kfd_destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		     enum kfd_preempt_type type,
+		     unsigned int timeout, uint32_t pipe_id,
+		     uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout);
+}
+
+bool kfd_is_occupied_sdma(struct mqd_manager *mm, void *mqd,
+		      uint64_t queue_address, uint32_t pipe_id,
+		      uint32_t queue_id)
+{
+	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 965e17c5dbb4..d81ae0699300 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -100,6 +100,20 @@ struct mqd_manager {
 				  u32 *ctl_stack_used_size,
 				  u32 *save_area_used_size);
 
+	void	(*get_checkpoint_info)(struct mqd_manager *mm, void *mqd, uint32_t *ctl_stack_size);
+
+	void	(*checkpoint_mqd)(struct mqd_manager *mm,
+				  void *mqd,
+				  void *mqd_dst,
+				  void *ctl_stack_dst);
+
+	void	(*restore_mqd)(struct mqd_manager *mm, void **mqd,
+				struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+				struct queue_properties *p,
+				const void *mqd_src,
+				const void *ctl_stack_src,
+				const u32 ctl_stack_size);
+
 #if defined(CONFIG_DEBUG_FS)
 	int	(*debugfs_show_mqd)(struct seq_file *m, void *data);
 #endif
@@ -122,4 +136,31 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		const uint32_t *cu_mask, uint32_t cu_mask_count,
 		uint32_t *se_mask);
 
+int kfd_hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+		uint32_t pipe_id, uint32_t queue_id,
+		struct queue_properties *p, struct mm_struct *mms);
+
+int kfd_destroy_mqd_cp(struct mqd_manager *mm, void *mqd,
+		enum kfd_preempt_type type, unsigned int timeout,
+		uint32_t pipe_id, uint32_t queue_id);
+
+void kfd_free_mqd_cp(struct mqd_manager *mm, void *mqd,
+		struct kfd_mem_obj *mqd_mem_obj);
+
+bool kfd_is_occupied_cp(struct mqd_manager *mm, void *mqd,
+		 uint64_t queue_address, uint32_t pipe_id,
+		 uint32_t queue_id);
+
+int kfd_load_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		uint32_t pipe_id, uint32_t queue_id,
+		struct queue_properties *p, struct mm_struct *mms);
+
+int kfd_destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
+		enum kfd_preempt_type type, unsigned int timeout,
+		uint32_t pipe_id, uint32_t queue_id);
+
+bool kfd_is_occupied_sdma(struct mqd_manager *mm, void *mqd,
+		uint64_t queue_address, uint32_t pipe_id,
+		uint32_t queue_id);
+
 #endif /* KFD_MQD_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index e9a8e21e144e..06aae5df6a37 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -156,13 +156,6 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 	mm->update_mqd(mm, m, q, NULL);
 }
 
-static void free_mqd(struct mqd_manager *mm, void *mqd,
-			struct kfd_mem_obj *mqd_mem_obj)
-{
-	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
-}
-
-
 static int load_mqd(struct mqd_manager *mm, void *mqd, uint32_t pipe_id,
 		    uint32_t queue_id, struct queue_properties *p,
 		    struct mm_struct *mms)
@@ -176,15 +169,6 @@ static int load_mqd(struct mqd_manager *mm, void *mqd, uint32_t pipe_id,
 					  wptr_shift, wptr_mask, mms);
 }
 
-static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
-			 uint32_t pipe_id, uint32_t queue_id,
-			 struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd,
-					       (uint32_t __user *)p->write_ptr,
-					       mms);
-}
-
 static void __update_mqd(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q, struct mqd_update_info *minfo,
 			unsigned int atc_bit)
@@ -271,42 +255,75 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
-static int destroy_mqd(struct mqd_manager *mm, void *mqd,
-			enum kfd_preempt_type type,
-			unsigned int timeout, uint32_t pipe_id,
-			uint32_t queue_id)
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
 {
-	return mm->dev->kfd2kgd->hqd_destroy(mm->dev->adev, mqd, type, timeout,
-					pipe_id, queue_id);
+	struct cik_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct cik_mqd));
 }
 
-/*
- * preempt type here is ignored because there is only one way
- * to preempt sdma queue
- */
-static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
-				enum kfd_preempt_type type,
-				unsigned int timeout, uint32_t pipe_id,
-				uint32_t queue_id)
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout);
+	uint64_t addr;
+	struct cik_mqd *m;
+
+	m = (struct cik_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control = DOORBELL_OFFSET(qp->doorbell_off);
+
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
 }
 
-static bool is_occupied(struct mqd_manager *mm, void *mqd,
-			uint64_t queue_address,	uint32_t pipe_id,
-			uint32_t queue_id)
+static void checkpoint_mqd_sdma(struct mqd_manager *mm,
+				void *mqd,
+				void *mqd_dst,
+				void *ctl_stack_dst)
 {
+	struct cik_sdma_rlc_registers *m;
 
-	return mm->dev->kfd2kgd->hqd_is_occupied(mm->dev->adev, queue_address,
-					pipe_id, queue_id);
+	m = get_sdma_mqd(mqd);
 
+	memcpy(mqd_dst, m, sizeof(struct cik_sdma_rlc_registers));
 }
 
-static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
-			uint64_t queue_address,	uint32_t pipe_id,
-			uint32_t queue_id)
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+				struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+				struct queue_properties *qp,
+				const void *mqd_src,
+				const void *ctl_stack_src, const u32 ctl_stack_size)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
+	uint64_t addr;
+	struct cik_sdma_rlc_registers *m;
+
+	m = (struct cik_sdma_rlc_registers *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	m->sdma_rlc_doorbell =
+		qp->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	qp->is_active = 0;
 }
 
 /*
@@ -389,11 +406,13 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_CP:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 		mqd->mqd_size = sizeof(struct cik_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -405,8 +424,8 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		mqd->free_mqd = free_mqd_hiq_sdma;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd_hiq;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct cik_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -416,11 +435,11 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_DIQ:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd_hiq;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct cik_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -430,10 +449,12 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_sdma_mqd;
 		mqd->init_mqd = init_mqd_sdma;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd_sdma;
+		mqd->load_mqd = kfd_load_mqd_sdma;
 		mqd->update_mqd = update_mqd_sdma;
-		mqd->destroy_mqd = destroy_mqd_sdma;
-		mqd->is_occupied = is_occupied_sdma;
+		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
+		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+		mqd->restore_mqd = restore_mqd_sdma;
 		mqd->mqd_size = sizeof(struct cik_sdma_rlc_registers);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index d74d8a6ac27a..88228009ded4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -154,14 +154,6 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 	return r;
 }
 
-static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
-			    uint32_t pipe_id, uint32_t queue_id,
-			    struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->adev, mqd, pipe_id,
-					      queue_id, p->doorbell_off);
-}
-
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q,
 			struct mqd_update_info *minfo)
@@ -233,31 +225,6 @@ static uint32_t read_doorbell_id(void *mqd)
 	return m->queue_doorbell_id0;
 }
 
-static int destroy_mqd(struct mqd_manager *mm, void *mqd,
-		       enum kfd_preempt_type type,
-		       unsigned int timeout, uint32_t pipe_id,
-		       uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_destroy
-		(mm->dev->adev, mqd, type, timeout,
-		 pipe_id, queue_id);
-}
-
-static void free_mqd(struct mqd_manager *mm, void *mqd,
-			struct kfd_mem_obj *mqd_mem_obj)
-{
-	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
-}
-
-static bool is_occupied(struct mqd_manager *mm, void *mqd,
-			uint64_t queue_address,	uint32_t pipe_id,
-			uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_is_occupied(
-		mm->dev->adev, queue_address,
-		pipe_id, queue_id);
-}
-
 static int get_wave_state(struct mqd_manager *mm, void *mqd,
 			  void __user *ctl_stack,
 			  u32 *ctl_stack_used_size,
@@ -285,6 +252,42 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct v10_compute_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v10_compute_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct v10_compute_mqd *m;
+
+	m = (struct v10_compute_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control =
+		qp->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
 static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -316,15 +319,6 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 	mm->update_mqd(mm, m, q, NULL);
 }
 
-static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		uint32_t pipe_id, uint32_t queue_id,
-		struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd,
-					       (uint32_t __user *)p->write_ptr,
-					       mms);
-}
-
 #define SDMA_RLC_DUMMY_DEFAULT 0xf
 
 static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
@@ -354,23 +348,41 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
-/*
- *  * preempt type here is ignored because there is only one way
- *  * to preempt sdma queue
- */
-static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		enum kfd_preempt_type type,
-		unsigned int timeout, uint32_t pipe_id,
-		uint32_t queue_id)
+static void checkpoint_mqd_sdma(struct mqd_manager *mm,
+				void *mqd,
+				void *mqd_dst,
+				void *ctl_stack_dst)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout);
+	struct v10_sdma_mqd *m;
+
+	m = get_sdma_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v10_sdma_mqd));
 }
 
-static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
-		uint64_t queue_address, uint32_t pipe_id,
-		uint32_t queue_id)
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+			     struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			     struct queue_properties *qp,
+			     const void *mqd_src,
+			     const void *ctl_stack_src,
+			     const u32 ctl_stack_size)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
+	uint64_t addr;
+	struct v10_sdma_mqd *m;
+
+	m = (struct v10_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	m->sdmax_rlcx_doorbell_offset =
+		qp->doorbell_off << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	qp->is_active = 0;
 }
 
 #if defined(CONFIG_DEBUG_FS)
@@ -410,13 +422,15 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		pr_debug("%s@%i\n", __func__, __LINE__);
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
 		mqd->get_wave_state = get_wave_state;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
 #endif
@@ -427,10 +441,10 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->load_mqd = kfd_hiq_load_mqd_kiq;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -441,11 +455,11 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_DIQ:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -456,10 +470,12 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_sdma_mqd;
 		mqd->init_mqd = init_mqd_sdma;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd_sdma;
+		mqd->load_mqd = kfd_load_mqd_sdma;
 		mqd->update_mqd = update_mqd_sdma;
-		mqd->destroy_mqd = destroy_mqd_sdma;
-		mqd->is_occupied = is_occupied_sdma;
+		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
+		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+		mqd->restore_mqd = restore_mqd_sdma;
 		mqd->mqd_size = sizeof(struct v10_sdma_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 326eb2285029..dff58ee53557 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -204,14 +204,6 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 					  wptr_shift, 0, mms);
 }
 
-static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
-			    uint32_t pipe_id, uint32_t queue_id,
-			    struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->adev, mqd, pipe_id,
-					      queue_id, p->doorbell_off);
-}
-
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q,
 			struct mqd_update_info *minfo)
@@ -285,38 +277,6 @@ static uint32_t read_doorbell_id(void *mqd)
 	return m->queue_doorbell_id0;
 }
 
-static int destroy_mqd(struct mqd_manager *mm, void *mqd,
-			enum kfd_preempt_type type,
-			unsigned int timeout, uint32_t pipe_id,
-			uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_destroy
-		(mm->dev->adev, mqd, type, timeout,
-		pipe_id, queue_id);
-}
-
-static void free_mqd(struct mqd_manager *mm, void *mqd,
-			struct kfd_mem_obj *mqd_mem_obj)
-{
-	struct kfd_dev *kfd = mm->dev;
-
-	if (mqd_mem_obj->gtt_mem) {
-		amdgpu_amdkfd_free_gtt_mem(kfd->adev, mqd_mem_obj->gtt_mem);
-		kfree(mqd_mem_obj);
-	} else {
-		kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
-	}
-}
-
-static bool is_occupied(struct mqd_manager *mm, void *mqd,
-			uint64_t queue_address,	uint32_t pipe_id,
-			uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_is_occupied(
-		mm->dev->adev, queue_address,
-		pipe_id, queue_id);
-}
-
 static int get_wave_state(struct mqd_manager *mm, void *mqd,
 			  void __user *ctl_stack,
 			  u32 *ctl_stack_used_size,
@@ -340,6 +300,57 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
+static void get_checkpoint_info(struct mqd_manager *mm, void *mqd, u32 *ctl_stack_size)
+{
+	struct v9_mqd *m = get_mqd(mqd);
+
+	*ctl_stack_size = m->cp_hqd_cntl_stack_size;
+}
+
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct v9_mqd *m;
+	/* Control stack is located one page after MQD. */
+	void *ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v9_mqd));
+	memcpy(ctl_stack_dst, ctl_stack, m->cp_hqd_cntl_stack_size);
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct v9_mqd *m;
+	void *ctl_stack;
+
+	m = (struct v9_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	/* Control stack is located one page after MQD. */
+	ctl_stack = (void *)((uintptr_t)*mqd + PAGE_SIZE);
+	memcpy(ctl_stack, ctl_stack_src, ctl_stack_size);
+
+	m->cp_hqd_pq_doorbell_control =
+		qp->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+				m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
 static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -371,15 +382,6 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 	mm->update_mqd(mm, m, q, NULL);
 }
 
-static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		uint32_t pipe_id, uint32_t queue_id,
-		struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd,
-					       (uint32_t __user *)p->write_ptr,
-					       mms);
-}
-
 #define SDMA_RLC_DUMMY_DEFAULT 0xf
 
 static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
@@ -409,23 +411,40 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
-/*
- *  * preempt type here is ignored because there is only one way
- *  * to preempt sdma queue
- */
-static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		enum kfd_preempt_type type,
-		unsigned int timeout, uint32_t pipe_id,
-		uint32_t queue_id)
+static void checkpoint_mqd_sdma(struct mqd_manager *mm,
+				void *mqd,
+				void *mqd_dst,
+				void *ctl_stack_dst)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout);
+	struct v9_sdma_mqd *m;
+
+	m = get_sdma_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct v9_sdma_mqd));
 }
 
-static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
-		uint64_t queue_address, uint32_t pipe_id,
-		uint32_t queue_id)
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+			     struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			     struct queue_properties *qp,
+			     const void *mqd_src,
+			     const void *ctl_stack_src, const u32 ctl_stack_size)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
+	uint64_t addr;
+	struct v9_sdma_mqd *m;
+
+	m = (struct v9_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	m->sdmax_rlcx_doorbell_offset =
+		qp->doorbell_off << SDMA0_RLC0_DOORBELL_OFFSET__OFFSET__SHIFT;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	qp->is_active = 0;
 }
 
 #if defined(CONFIG_DEBUG_FS)
@@ -464,12 +483,15 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_CP:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->get_wave_state = get_wave_state;
+		mqd->get_checkpoint_info = get_checkpoint_info;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 		mqd->mqd_size = sizeof(struct v9_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -479,10 +501,10 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->load_mqd = kfd_hiq_load_mqd_kiq;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v9_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -492,11 +514,11 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_DIQ:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct v9_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -506,10 +528,12 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_sdma_mqd;
 		mqd->init_mqd = init_mqd_sdma;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd_sdma;
+		mqd->load_mqd = kfd_load_mqd_sdma;
 		mqd->update_mqd = update_mqd_sdma;
-		mqd->destroy_mqd = destroy_mqd_sdma;
-		mqd->is_occupied = is_occupied_sdma;
+		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
+		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+		mqd->restore_mqd = restore_mqd_sdma;
 		mqd->mqd_size = sizeof(struct v9_sdma_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index d456e950ce1d..86fc5decacf0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -259,31 +259,6 @@ static void update_mqd_tonga(struct mqd_manager *mm, void *mqd,
 	__update_mqd(mm, mqd, q, minfo, MTYPE_UC, 0);
 }
 
-static int destroy_mqd(struct mqd_manager *mm, void *mqd,
-			enum kfd_preempt_type type,
-			unsigned int timeout, uint32_t pipe_id,
-			uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_destroy
-		(mm->dev->adev, mqd, type, timeout,
-		pipe_id, queue_id);
-}
-
-static void free_mqd(struct mqd_manager *mm, void *mqd,
-			struct kfd_mem_obj *mqd_mem_obj)
-{
-	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
-}
-
-static bool is_occupied(struct mqd_manager *mm, void *mqd,
-			uint64_t queue_address,	uint32_t pipe_id,
-			uint32_t queue_id)
-{
-	return mm->dev->kfd2kgd->hqd_is_occupied(
-		mm->dev->adev, queue_address,
-		pipe_id, queue_id);
-}
-
 static int get_wave_state(struct mqd_manager *mm, void *mqd,
 			  void __user *ctl_stack,
 			  u32 *ctl_stack_used_size,
@@ -306,6 +281,48 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	return 0;
 }
 
+static void get_checkpoint_info(struct mqd_manager *mm, void *mqd, u32 *ctl_stack_size)
+{
+	/* Control stack is stored in user mode */
+	*ctl_stack_size = 0;
+}
+
+static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
+{
+	struct vi_mqd *m;
+
+	m = get_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct vi_mqd));
+}
+
+static void restore_mqd(struct mqd_manager *mm, void **mqd,
+			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			struct queue_properties *qp,
+			const void *mqd_src,
+			const void *ctl_stack_src, const u32 ctl_stack_size)
+{
+	uint64_t addr;
+	struct vi_mqd *m;
+
+	m = (struct vi_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	m->cp_hqd_pq_doorbell_control =
+		qp->doorbell_off <<
+			CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT;
+	pr_debug("cp_hqd_pq_doorbell_control 0x%x\n",
+			m->cp_hqd_pq_doorbell_control);
+
+	qp->is_active = 0;
+}
+
 static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -343,15 +360,6 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 	mm->update_mqd(mm, m, q, NULL);
 }
 
-static int load_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		uint32_t pipe_id, uint32_t queue_id,
-		struct queue_properties *p, struct mm_struct *mms)
-{
-	return mm->dev->kfd2kgd->hqd_sdma_load(mm->dev->adev, mqd,
-					       (uint32_t __user *)p->write_ptr,
-					       mms);
-}
-
 static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q,
 			struct mqd_update_info *minfo)
@@ -380,27 +388,45 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
-/*
- *  * preempt type here is ignored because there is only one way
- *  * to preempt sdma queue
- */
-static int destroy_mqd_sdma(struct mqd_manager *mm, void *mqd,
-		enum kfd_preempt_type type,
-		unsigned int timeout, uint32_t pipe_id,
-		uint32_t queue_id)
+static void checkpoint_mqd_sdma(struct mqd_manager *mm,
+				void *mqd,
+				void *mqd_dst,
+				void *ctl_stack_dst)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_destroy(mm->dev->adev, mqd, timeout);
+	struct vi_sdma_mqd *m;
+
+	m = get_sdma_mqd(mqd);
+
+	memcpy(mqd_dst, m, sizeof(struct vi_sdma_mqd));
 }
 
-static bool is_occupied_sdma(struct mqd_manager *mm, void *mqd,
-		uint64_t queue_address, uint32_t pipe_id,
-		uint32_t queue_id)
+static void restore_mqd_sdma(struct mqd_manager *mm, void **mqd,
+			     struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
+			     struct queue_properties *qp,
+			     const void *mqd_src,
+			     const void *ctl_stack_src, const u32 ctl_stack_size)
 {
-	return mm->dev->kfd2kgd->hqd_sdma_is_occupied(mm->dev->adev, mqd);
+	uint64_t addr;
+	struct vi_sdma_mqd *m;
+
+	m = (struct vi_sdma_mqd *) mqd_mem_obj->cpu_ptr;
+	addr = mqd_mem_obj->gpu_addr;
+
+	memcpy(m, mqd_src, sizeof(*m));
+
+	m->sdmax_rlcx_doorbell =
+		qp->doorbell_off << SDMA0_RLC0_DOORBELL__OFFSET__SHIFT;
+
+	*mqd = m;
+	if (gart_addr)
+		*gart_addr = addr;
+
+	qp->is_active = 0;
 }
 
 #if defined(CONFIG_DEBUG_FS)
 
+
 static int debugfs_show_mqd(struct seq_file *m, void *data)
 {
 	seq_hex_dump(m, "    ", DUMP_PREFIX_OFFSET, 32, 4,
@@ -435,12 +461,15 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_CP:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->get_wave_state = get_wave_state;
+		mqd->get_checkpoint_info = get_checkpoint_info;
+		mqd->checkpoint_mqd = checkpoint_mqd;
+		mqd->restore_mqd = restore_mqd;
 		mqd->mqd_size = sizeof(struct vi_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -452,8 +481,8 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		mqd->free_mqd = free_mqd_hiq_sdma;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd_hiq;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct vi_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -463,11 +492,11 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	case KFD_MQD_TYPE_DIQ:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
-		mqd->free_mqd = free_mqd;
+		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->load_mqd = load_mqd;
 		mqd->update_mqd = update_mqd_hiq;
-		mqd->destroy_mqd = destroy_mqd;
-		mqd->is_occupied = is_occupied;
+		mqd->destroy_mqd = kfd_destroy_mqd_cp;
+		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->mqd_size = sizeof(struct vi_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd;
@@ -477,10 +506,12 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_sdma_mqd;
 		mqd->init_mqd = init_mqd_sdma;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd_sdma;
+		mqd->load_mqd = kfd_load_mqd_sdma;
 		mqd->update_mqd = update_mqd_sdma;
-		mqd->destroy_mqd = destroy_mqd_sdma;
-		mqd->is_occupied = is_occupied_sdma;
+		mqd->destroy_mqd = kfd_destroy_mqd_sdma;
+		mqd->is_occupied = kfd_is_occupied_sdma;
+		mqd->checkpoint_mqd = checkpoint_mqd_sdma;
+		mqd->restore_mqd = restore_mqd_sdma;
 		mqd->mqd_size = sizeof(struct vi_sdma_mqd);
 #if defined(CONFIG_DEBUG_FS)
 		mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ea68f3b3a4e9..b6790a637f5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -121,7 +121,26 @@
  */
 #define KFD_QUEUE_DOORBELL_MIRROR_OFFSET 512
 
-
+/**
+ * enum kfd_ioctl_flags - KFD ioctl flags
+ * Various flags that can be set in &amdkfd_ioctl_desc.flags to control how
+ * userspace can use a given ioctl.
+ */
+enum kfd_ioctl_flags {
+	/*
+	 * @KFD_IOC_FLAG_CHECKPOINT_RESTORE:
+	 * Certain KFD ioctls such as AMDKFD_IOC_CRIU_OP can potentially
+	 * perform privileged operations and load arbitrary data into MQDs and
+	 * eventually HQD registers when the queue is mapped by HWS. In order to
+	 * prevent this we should perform additional security checks.
+	 *
+	 * This is equivalent to callers with the CHECKPOINT_RESTORE capability.
+	 *
+	 * Note: Since earlier versions of docker do not support CHECKPOINT_RESTORE,
+	 * we also allow ioctls with SYS_ADMIN capability.
+	 */
+	KFD_IOC_FLAG_CHECKPOINT_RESTORE = BIT(0),
+};
 /*
  * Kernel module parameter to specify maximum number of supported queues per
  * device
@@ -281,9 +300,6 @@ struct kfd_dev {
 	 */
 	bool interrupts_active;
 
-	/* Debug manager */
-	struct kfd_dbgmgr *dbgmgr;
-
 	/* Firmware versions */
 	uint16_t mec_fw_version;
 	uint16_t mec2_fw_version;
@@ -442,6 +458,7 @@ enum KFD_QUEUE_PRIORITY {
  * it's user mode or kernel mode queue.
  *
  */
+
 struct queue_properties {
 	enum kfd_queue_type type;
 	enum kfd_queue_format format;
@@ -754,6 +771,12 @@ struct kfd_process_device {
 	uint64_t faults;
 	uint64_t page_in;
 	uint64_t page_out;
+	/*
+	 * If this process has been checkpointed before, then the user
+	 * application will use the original gpu_id on the
+	 * checkpointed node to refer to this device.
+	 */
+	uint32_t user_gpu_id;
 };
 
 #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd)
@@ -764,6 +787,7 @@ struct svm_range_list {
 	struct list_head		list;
 	struct work_struct		deferred_list_work;
 	struct list_head		deferred_range_list;
+	struct list_head                criu_svm_metadata_list;
 	spinlock_t			deferred_list_lock;
 	atomic_t			evicted_ranges;
 	atomic_t			drain_pagefaults;
@@ -858,6 +882,8 @@ struct kfd_process {
 	bool xnack_enabled;
 
 	atomic_t poison;
+	/* Queues are in paused stated because we are in the process of doing a CRIU checkpoint */
+	bool queues_paused;
 };
 
 #define KFD_PROCESS_TABLE_SIZE 5 /* bits: 32 entries */
@@ -911,6 +937,11 @@ 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_get_user_gpu_id(struct kfd_process *p, uint32_t actual_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,
@@ -932,6 +963,7 @@ void *kfd_process_device_translate_handle(struct kfd_process_device *p,
 					int handle);
 void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
 					int handle);
+struct kfd_process *kfd_lookup_process_by_pid(struct pid *pid);
 
 /* PASIDs */
 int kfd_pasid_init(void);
@@ -1006,6 +1038,116 @@ void kfd_process_set_trap_handler(struct qcm_process_device *qpd,
 				  uint64_t tba_addr,
 				  uint64_t tma_addr);
 
+/* CRIU */
+/*
+ * Need to increment KFD_CRIU_PRIV_VERSION each time a change is made to any of the CRIU private
+ * structures:
+ * kfd_criu_process_priv_data
+ * kfd_criu_device_priv_data
+ * kfd_criu_bo_priv_data
+ * kfd_criu_queue_priv_data
+ * kfd_criu_event_priv_data
+ * kfd_criu_svm_range_priv_data
+ */
+
+#define KFD_CRIU_PRIV_VERSION 1
+
+struct kfd_criu_process_priv_data {
+	uint32_t version;
+	uint32_t xnack_mode;
+};
+
+struct kfd_criu_device_priv_data {
+	/* For future use */
+	uint64_t reserved;
+};
+
+struct kfd_criu_bo_priv_data {
+	uint64_t user_addr;
+	uint32_t idr_handle;
+	uint32_t mapped_gpuids[MAX_GPU_INSTANCE];
+};
+
+/*
+ * The first 4 bytes of kfd_criu_queue_priv_data, kfd_criu_event_priv_data,
+ * kfd_criu_svm_range_priv_data is the object type
+ */
+enum kfd_criu_object_type {
+	KFD_CRIU_OBJECT_TYPE_QUEUE,
+	KFD_CRIU_OBJECT_TYPE_EVENT,
+	KFD_CRIU_OBJECT_TYPE_SVM_RANGE,
+};
+
+struct kfd_criu_svm_range_priv_data {
+	uint32_t object_type;
+	uint64_t start_addr;
+	uint64_t size;
+	/* Variable length array of attributes */
+	struct kfd_ioctl_svm_attribute attrs[0];
+};
+
+struct kfd_criu_queue_priv_data {
+	uint32_t object_type;
+	uint64_t q_address;
+	uint64_t q_size;
+	uint64_t read_ptr_addr;
+	uint64_t write_ptr_addr;
+	uint64_t doorbell_off;
+	uint64_t eop_ring_buffer_address;
+	uint64_t ctx_save_restore_area_address;
+	uint32_t gpu_id;
+	uint32_t type;
+	uint32_t format;
+	uint32_t q_id;
+	uint32_t priority;
+	uint32_t q_percent;
+	uint32_t doorbell_id;
+	uint32_t is_gws;
+	uint32_t sdma_id;
+	uint32_t eop_ring_buffer_size;
+	uint32_t ctx_save_restore_area_size;
+	uint32_t ctl_stack_size;
+	uint32_t mqd_size;
+};
+
+struct kfd_criu_event_priv_data {
+	uint32_t object_type;
+	uint64_t user_handle;
+	uint32_t event_id;
+	uint32_t auto_reset;
+	uint32_t type;
+	uint32_t signaled;
+
+	union {
+		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
+	};
+};
+
+int kfd_process_get_queue_info(struct kfd_process *p,
+			       uint32_t *num_queues,
+			       uint64_t *priv_data_sizes);
+
+int kfd_criu_checkpoint_queues(struct kfd_process *p,
+			 uint8_t __user *user_priv_data,
+			 uint64_t *priv_data_offset);
+
+int kfd_criu_restore_queue(struct kfd_process *p,
+			   uint8_t __user *user_priv_data,
+			   uint64_t *priv_data_offset,
+			   uint64_t max_priv_data_size);
+
+int kfd_criu_checkpoint_events(struct kfd_process *p,
+			 uint8_t __user *user_priv_data,
+			 uint64_t *priv_data_offset);
+
+int kfd_criu_restore_event(struct file *devkfd,
+			   struct kfd_process *p,
+			   uint8_t __user *user_priv_data,
+			   uint64_t *priv_data_offset,
+			   uint64_t max_priv_data_size);
+/* CRIU - End */
+
 /* Queue Context Management */
 int init_queue(struct queue **q, const struct queue_properties *properties);
 void uninit_queue(struct queue *q);
@@ -1029,7 +1171,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
-int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid);
+int kfd_dqm_evict_pasid(struct device_queue_manager *dqm, u32 pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -1047,6 +1189,9 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct file *f,
 			    struct queue_properties *properties,
 			    unsigned int *qid,
+			    const struct kfd_criu_queue_priv_data *q_data,
+			    const void *restore_mqd,
+			    const void *restore_ctl_stack,
 			    uint32_t *p_doorbell_offset_in_process);
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue_properties(struct process_queue_manager *pqm, unsigned int qid,
@@ -1069,6 +1214,10 @@ int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
 			      uint64_t fence_value,
 			      unsigned int timeout_ms);
 
+int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm,
+				  unsigned int qid,
+				  u32 *mqd_size,
+				  u32 *ctl_stack_size);
 /* Packet Manager */
 
 #define KFD_FENCE_COMPLETED (100)
@@ -1160,12 +1309,14 @@ void kfd_signal_iommu_event(struct kfd_dev *dev,
 void kfd_signal_hw_exception_event(u32 pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
-int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
-		       uint64_t size);
+int kfd_kmap_event_page(struct kfd_process *p, uint64_t event_page_offset);
+
 int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint32_t event_type, bool auto_reset, uint32_t node_id,
 		     uint32_t *event_id, uint32_t *event_trigger_data,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
+
+int kfd_get_num_events(struct kfd_process *p);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
 void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
@@ -1177,8 +1328,6 @@ void kfd_signal_poison_consumed_event(struct kfd_dev *dev, u32 pasid);
 
 void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type);
 
-int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
-
 bool kfd_is_locked(void);
 
 /* Compute profile */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d1145da5348f..8c6a48add76e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -40,7 +40,6 @@ struct mm_struct;
 
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
-#include "kfd_dbgmgr.h"
 #include "kfd_iommu.h"
 #include "kfd_svm.h"
 
@@ -64,7 +63,8 @@ static struct workqueue_struct *kfd_process_wq;
  */
 static struct workqueue_struct *kfd_restore_wq;
 
-static struct kfd_process *find_process(const struct task_struct *thread);
+static struct kfd_process *find_process(const struct task_struct *thread,
+					bool ref);
 static void kfd_process_ref_release(struct kref *ref);
 static struct kfd_process *create_process(const struct task_struct *thread);
 static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep);
@@ -715,7 +715,8 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd,
 	int err;
 
 	err = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(kdev->adev, gpu_va, size,
-						 pdd->drm_priv, mem, NULL, flags);
+						 pdd->drm_priv, mem, NULL,
+						 flags, false);
 	if (err)
 		goto err_alloc_mem;
 
@@ -816,7 +817,7 @@ struct kfd_process *kfd_create_process(struct file *filep)
 	mutex_lock(&kfd_processes_mutex);
 
 	/* A prior open of /dev/kfd could have already created the process. */
-	process = find_process(thread);
+	process = find_process(thread, false);
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
@@ -884,7 +885,7 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 	if (thread->group_leader->mm != thread->mm)
 		return ERR_PTR(-EINVAL);
 
-	process = find_process(thread);
+	process = find_process(thread, false);
 	if (!process)
 		return ERR_PTR(-EINVAL);
 
@@ -903,13 +904,16 @@ static struct kfd_process *find_process_by_mm(const struct mm_struct *mm)
 	return NULL;
 }
 
-static struct kfd_process *find_process(const struct task_struct *thread)
+static struct kfd_process *find_process(const struct task_struct *thread,
+					bool ref)
 {
 	struct kfd_process *p;
 	int idx;
 
 	idx = srcu_read_lock(&kfd_processes_srcu);
 	p = find_process_by_mm(thread->mm);
+	if (p && ref)
+		kref_get(&p->ref);
 	srcu_read_unlock(&kfd_processes_srcu, idx);
 
 	return p;
@@ -920,6 +924,26 @@ void kfd_unref_process(struct kfd_process *p)
 	kref_put(&p->ref, kfd_process_ref_release);
 }
 
+/* This increments the process->ref counter. */
+struct kfd_process *kfd_lookup_process_by_pid(struct pid *pid)
+{
+	struct task_struct *task = NULL;
+	struct kfd_process *p    = NULL;
+
+	if (!pid) {
+		task = current;
+		get_task_struct(task);
+	} else {
+		task = get_pid_task(pid, PIDTYPE_PID);
+	}
+
+	if (task) {
+		p = find_process(task, true);
+		put_task_struct(task);
+	}
+
+	return p;
+}
 
 static void kfd_process_device_free_bos(struct kfd_process_device *pdd)
 {
@@ -1133,7 +1157,6 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 					struct mm_struct *mm)
 {
 	struct kfd_process *p;
-	int i;
 
 	/*
 	 * The kfd_process structure can not be free because the
@@ -1150,27 +1173,9 @@ 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);
 
-	/* Iterate over all process device data structures and if the
-	 * pdd is in debug mode, we should first force unregistration,
-	 * then we will be able to destroy the queues
-	 */
-	for (i = 0; i < p->n_pdds; i++) {
-		struct kfd_dev *dev = p->pdds[i]->dev;
-
-		mutex_lock(kfd_get_dbgmgr_mutex());
-		if (dev && dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) {
-			if (!kfd_dbgmgr_unregister(dev->dbgmgr, p)) {
-				kfd_dbgmgr_destroy(dev->dbgmgr);
-				dev->dbgmgr = NULL;
-			}
-		}
-		mutex_unlock(kfd_get_dbgmgr_mutex());
-	}
-
 	kfd_process_dequeue_from_all_devices(p);
 	pqm_uninit(&p->pqm);
 
@@ -1360,6 +1365,7 @@ static struct kfd_process *create_process(const struct task_struct *thread)
 	process->mm = thread->mm;
 	process->lead_thread = thread->group_leader;
 	process->n_pdds = 0;
+	process->queues_paused = false;
 	INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker);
 	INIT_DELAYED_WORK(&process->restore_work, restore_process_worker);
 	process->last_restore_timestamp = get_jiffies_64();
@@ -1501,6 +1507,7 @@ 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;
 
@@ -1771,7 +1778,7 @@ 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)
+		if (p->pdds[i] && gpu_id == p->pdds[i]->user_gpu_id)
 			return i;
 	return -EINVAL;
 }
@@ -1784,7 +1791,7 @@ kfd_process_gpuid_from_adev(struct kfd_process *p, struct amdgpu_device *adev,
 
 	for (i = 0; i < p->n_pdds; i++)
 		if (p->pdds[i] && p->pdds[i]->dev->adev == adev) {
-			*gpuid = p->pdds[i]->dev->id;
+			*gpuid = p->pdds[i]->user_gpu_id;
 			*gpuidx = i;
 			return 0;
 		}
@@ -1956,6 +1963,37 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type)
 	}
 }
 
+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;
+		}
+	}
+	return NULL;
+}
+
+int kfd_process_get_user_gpu_id(struct kfd_process *p, uint32_t actual_gpu_id)
+{
+	int i;
+
+	if (!actual_gpu_id)
+		return 0;
+
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+
+		if (pdd->dev->id == actual_gpu_id)
+			return pdd->user_gpu_id;
+	}
+	return -EINVAL;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 int kfd_debugfs_mqds_by_process(struct seq_file *m, void *data)
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 5e5c84a8e1ef..70ea4849e6a2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -42,6 +42,20 @@ static inline struct process_queue_node *get_queue_by_qid(
 	return NULL;
 }
 
+static int assign_queue_slot_by_qid(struct process_queue_manager *pqm,
+				    unsigned int qid)
+{
+	if (qid >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
+		return -EINVAL;
+
+	if (__test_and_set_bit(qid, pqm->queue_slot_bitmap)) {
+		pr_err("Cannot create new queue because requested qid(%u) is in use\n", qid);
+		return -ENOSPC;
+	}
+
+	return 0;
+}
+
 static int find_available_queue_slot(struct process_queue_manager *pqm,
 					unsigned int *qid)
 {
@@ -193,6 +207,9 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct file *f,
 			    struct queue_properties *properties,
 			    unsigned int *qid,
+			    const struct kfd_criu_queue_priv_data *q_data,
+			    const void *restore_mqd,
+			    const void *restore_ctl_stack,
 			    uint32_t *p_doorbell_offset_in_process)
 {
 	int retval;
@@ -224,7 +241,12 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	if (pdd->qpd.queue_count >= max_queues)
 		return -ENOSPC;
 
-	retval = find_available_queue_slot(pqm, qid);
+	if (q_data) {
+		retval = assign_queue_slot_by_qid(pqm, q_data->q_id);
+		*qid = q_data->q_id;
+	} else
+		retval = find_available_queue_slot(pqm, qid);
+
 	if (retval != 0)
 		return retval;
 
@@ -252,7 +274,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;
-		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data,
+						    restore_mqd, restore_ctl_stack);
 		print_queue(q);
 		break;
 
@@ -272,7 +295,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		pqn->q = q;
 		pqn->kq = NULL;
-		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd);
+		retval = dev->dqm->ops.create_queue(dev->dqm, q, &pdd->qpd, q_data,
+						    restore_mqd, restore_ctl_stack);
 		print_queue(q);
 		break;
 	case KFD_QUEUE_TYPE_DIQ:
@@ -497,6 +521,348 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
 						       save_area_used_size);
 }
 
+static int get_queue_data_sizes(struct kfd_process_device *pdd,
+				struct queue *q,
+				uint32_t *mqd_size,
+				uint32_t *ctl_stack_size)
+{
+	int ret;
+
+	ret = pqm_get_queue_checkpoint_info(&pdd->process->pqm,
+					    q->properties.queue_id,
+					    mqd_size,
+					    ctl_stack_size);
+	if (ret)
+		pr_err("Failed to get queue dump info (%d)\n", ret);
+
+	return ret;
+}
+
+int kfd_process_get_queue_info(struct kfd_process *p,
+			       uint32_t *num_queues,
+			       uint64_t *priv_data_sizes)
+{
+	uint32_t extra_data_sizes = 0;
+	struct queue *q;
+	int i;
+	int ret;
+
+	*num_queues = 0;
+
+	/* Run over all PDDs of the process */
+	for (i = 0; i < p->n_pdds; i++) {
+		struct kfd_process_device *pdd = p->pdds[i];
+
+		list_for_each_entry(q, &pdd->qpd.queues_list, list) {
+			if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
+				q->properties.type == KFD_QUEUE_TYPE_SDMA ||
+				q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) {
+				uint32_t mqd_size, ctl_stack_size;
+
+				*num_queues = *num_queues + 1;
+
+				ret = get_queue_data_sizes(pdd, q, &mqd_size, &ctl_stack_size);
+				if (ret)
+					return ret;
+
+				extra_data_sizes += mqd_size + ctl_stack_size;
+			} else {
+				pr_err("Unsupported queue type (%d)\n", q->properties.type);
+				return -EOPNOTSUPP;
+			}
+		}
+	}
+	*priv_data_sizes = extra_data_sizes +
+				(*num_queues * sizeof(struct kfd_criu_queue_priv_data));
+
+	return 0;
+}
+
+static int pqm_checkpoint_mqd(struct process_queue_manager *pqm,
+			      unsigned int qid,
+			      void *mqd,
+			      void *ctl_stack)
+{
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for operation\n", qid);
+		return -EFAULT;
+	}
+
+	if (!pqn->q->device->dqm->ops.checkpoint_mqd) {
+		pr_err("amdkfd: queue dumping not supported on this device\n");
+		return -EOPNOTSUPP;
+	}
+
+	return pqn->q->device->dqm->ops.checkpoint_mqd(pqn->q->device->dqm,
+						       pqn->q, mqd, ctl_stack);
+}
+
+static int criu_checkpoint_queue(struct kfd_process_device *pdd,
+			   struct queue *q,
+			   struct kfd_criu_queue_priv_data *q_data)
+{
+	uint8_t *mqd, *ctl_stack;
+	int ret;
+
+	mqd = (void *)(q_data + 1);
+	ctl_stack = mqd + q_data->mqd_size;
+
+	q_data->gpu_id = pdd->user_gpu_id;
+	q_data->type = q->properties.type;
+	q_data->format = q->properties.format;
+	q_data->q_id =  q->properties.queue_id;
+	q_data->q_address = q->properties.queue_address;
+	q_data->q_size = q->properties.queue_size;
+	q_data->priority = q->properties.priority;
+	q_data->q_percent = q->properties.queue_percent;
+	q_data->read_ptr_addr = (uint64_t)q->properties.read_ptr;
+	q_data->write_ptr_addr = (uint64_t)q->properties.write_ptr;
+	q_data->doorbell_id = q->doorbell_id;
+
+	q_data->sdma_id = q->sdma_id;
+
+	q_data->eop_ring_buffer_address =
+		q->properties.eop_ring_buffer_address;
+
+	q_data->eop_ring_buffer_size = q->properties.eop_ring_buffer_size;
+
+	q_data->ctx_save_restore_area_address =
+		q->properties.ctx_save_restore_area_address;
+
+	q_data->ctx_save_restore_area_size =
+		q->properties.ctx_save_restore_area_size;
+
+	ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack);
+	if (ret) {
+		pr_err("Failed checkpoint queue_mqd (%d)\n", ret);
+		return ret;
+	}
+
+	pr_debug("Dumping Queue: gpu_id:%x queue_id:%u\n", q_data->gpu_id, q_data->q_id);
+	return ret;
+}
+
+static int criu_checkpoint_queues_device(struct kfd_process_device *pdd,
+				   uint8_t __user *user_priv,
+				   unsigned int *q_index,
+				   uint64_t *queues_priv_data_offset)
+{
+	unsigned int q_private_data_size = 0;
+	uint8_t *q_private_data = NULL; /* Local buffer to store individual queue private data */
+	struct queue *q;
+	int ret = 0;
+
+	list_for_each_entry(q, &pdd->qpd.queues_list, list) {
+		struct kfd_criu_queue_priv_data *q_data;
+		uint64_t q_data_size;
+		uint32_t mqd_size;
+		uint32_t ctl_stack_size;
+
+		if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE &&
+			q->properties.type != KFD_QUEUE_TYPE_SDMA &&
+			q->properties.type != KFD_QUEUE_TYPE_SDMA_XGMI) {
+
+			pr_err("Unsupported queue type (%d)\n", q->properties.type);
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		ret = get_queue_data_sizes(pdd, q, &mqd_size, &ctl_stack_size);
+		if (ret)
+			break;
+
+		q_data_size = sizeof(*q_data) + mqd_size + ctl_stack_size;
+
+		/* Increase local buffer space if needed */
+		if (q_private_data_size < q_data_size) {
+			kfree(q_private_data);
+
+			q_private_data = kzalloc(q_data_size, GFP_KERNEL);
+			if (!q_private_data) {
+				ret = -ENOMEM;
+				break;
+			}
+			q_private_data_size = q_data_size;
+		}
+
+		q_data = (struct kfd_criu_queue_priv_data *)q_private_data;
+
+		/* data stored in this order: priv_data, mqd, ctl_stack */
+		q_data->mqd_size = mqd_size;
+		q_data->ctl_stack_size = ctl_stack_size;
+
+		ret = criu_checkpoint_queue(pdd, q, q_data);
+		if (ret)
+			break;
+
+		q_data->object_type = KFD_CRIU_OBJECT_TYPE_QUEUE;
+
+		ret = copy_to_user(user_priv + *queues_priv_data_offset,
+				q_data, q_data_size);
+		if (ret) {
+			ret = -EFAULT;
+			break;
+		}
+		*queues_priv_data_offset += q_data_size;
+		*q_index = *q_index + 1;
+	}
+
+	kfree(q_private_data);
+
+	return ret;
+}
+
+int kfd_criu_checkpoint_queues(struct kfd_process *p,
+			 uint8_t __user *user_priv_data,
+			 uint64_t *priv_data_offset)
+{
+	int ret = 0, pdd_index, q_index = 0;
+
+	for (pdd_index = 0; pdd_index < p->n_pdds; pdd_index++) {
+		struct kfd_process_device *pdd = p->pdds[pdd_index];
+
+		/*
+		 * criu_checkpoint_queues_device will copy data to user and update q_index and
+		 * queues_priv_data_offset
+		 */
+		ret = criu_checkpoint_queues_device(pdd, user_priv_data, &q_index,
+					      priv_data_offset);
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void set_queue_properties_from_criu(struct queue_properties *qp,
+					  struct kfd_criu_queue_priv_data *q_data)
+{
+	qp->is_interop = false;
+	qp->is_gws = q_data->is_gws;
+	qp->queue_percent = q_data->q_percent;
+	qp->priority = q_data->priority;
+	qp->queue_address = q_data->q_address;
+	qp->queue_size = q_data->q_size;
+	qp->read_ptr = (uint32_t *) q_data->read_ptr_addr;
+	qp->write_ptr = (uint32_t *) q_data->write_ptr_addr;
+	qp->eop_ring_buffer_address = q_data->eop_ring_buffer_address;
+	qp->eop_ring_buffer_size = q_data->eop_ring_buffer_size;
+	qp->ctx_save_restore_area_address = q_data->ctx_save_restore_area_address;
+	qp->ctx_save_restore_area_size = q_data->ctx_save_restore_area_size;
+	qp->ctl_stack_size = q_data->ctl_stack_size;
+	qp->type = q_data->type;
+	qp->format = q_data->format;
+}
+
+int kfd_criu_restore_queue(struct kfd_process *p,
+			   uint8_t __user *user_priv_ptr,
+			   uint64_t *priv_data_offset,
+			   uint64_t max_priv_data_size)
+{
+	uint8_t *mqd, *ctl_stack, *q_extra_data = NULL;
+	struct kfd_criu_queue_priv_data *q_data;
+	struct kfd_process_device *pdd;
+	uint64_t q_extra_data_size;
+	struct queue_properties qp;
+	unsigned int queue_id;
+	int ret = 0;
+
+	if (*priv_data_offset + sizeof(*q_data) > max_priv_data_size)
+		return -EINVAL;
+
+	q_data = kmalloc(sizeof(*q_data), GFP_KERNEL);
+	if (!q_data)
+		return -ENOMEM;
+
+	ret = copy_from_user(q_data, user_priv_ptr + *priv_data_offset, sizeof(*q_data));
+	if (ret) {
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	*priv_data_offset += sizeof(*q_data);
+	q_extra_data_size = q_data->ctl_stack_size + q_data->mqd_size;
+
+	if (*priv_data_offset + q_extra_data_size > max_priv_data_size) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	q_extra_data = kmalloc(q_extra_data_size, GFP_KERNEL);
+	if (!q_extra_data) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	ret = copy_from_user(q_extra_data, user_priv_ptr + *priv_data_offset, q_extra_data_size);
+	if (ret) {
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	*priv_data_offset += q_extra_data_size;
+
+	pdd = kfd_process_device_data_by_id(p, q_data->gpu_id);
+	if (!pdd) {
+		pr_err("Failed to get pdd\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+	/* data stored in this order: mqd, ctl_stack */
+	mqd = q_extra_data;
+	ctl_stack = mqd + q_data->mqd_size;
+
+	memset(&qp, 0, sizeof(qp));
+	set_queue_properties_from_criu(&qp, q_data);
+
+	print_queue_properties(&qp);
+
+	ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, mqd, ctl_stack,
+				NULL);
+	if (ret) {
+		pr_err("Failed to create new queue err:%d\n", ret);
+		ret = -EINVAL;
+	}
+
+exit:
+	if (ret)
+		pr_err("Failed to create queue (%d)\n", ret);
+	else
+		pr_debug("Queue id %d was restored successfully\n", queue_id);
+
+	kfree(q_data);
+
+	return ret;
+}
+
+int pqm_get_queue_checkpoint_info(struct process_queue_manager *pqm,
+				  unsigned int qid,
+				  uint32_t *mqd_size,
+				  uint32_t *ctl_stack_size)
+{
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for operation\n", qid);
+		return -EFAULT;
+	}
+
+	if (!pqn->q->device->dqm->ops.get_queue_checkpoint_info) {
+		pr_err("amdkfd: queue dumping not supported on this device\n");
+		return -EOPNOTSUPP;
+	}
+
+	pqn->q->device->dqm->ops.get_queue_checkpoint_info(pqn->q->device->dqm,
+						       pqn->q, mqd_size,
+						       ctl_stack_size);
+	return 0;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 int pqm_debugfs_mqds(struct seq_file *m, void *data)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index deae12dc777d..329a4c89f1e6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -222,7 +222,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 
 	len = snprintf(fifo_in, sizeof(fifo_in), "%x %llx:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
-		       atomic64_read(&dev->adev->smu.throttle_int_counter));
+		       amdgpu_dpm_get_thermal_throttling_counter(dev->adev));
 
 	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE,	fifo_in, len);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f2805ba74c80..b71d47afd243 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -45,6 +45,11 @@
  */
 #define AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING	2000
 
+struct criu_svm_metadata {
+	struct list_head list;
+	struct kfd_criu_svm_range_priv_data data;
+};
+
 static void svm_range_evict_svm_bo_worker(struct work_struct *work);
 static bool
 svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
@@ -1224,19 +1229,20 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
 			if (r)
 				break;
 		}
-		amdgpu_amdkfd_flush_gpu_tlb_pasid(pdd->dev->adev,
-					p->pasid, TLB_FLUSH_HEAVYWEIGHT);
+		kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
 	}
 
 	return r;
 }
 
 static int
-svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		     struct svm_range *prange, unsigned long offset,
-		     unsigned long npages, bool readonly, dma_addr_t *dma_addr,
-		     struct amdgpu_device *bo_adev, struct dma_fence **fence)
+svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange,
+		     unsigned long offset, unsigned long npages, bool readonly,
+		     dma_addr_t *dma_addr, struct amdgpu_device *bo_adev,
+		     struct dma_fence **fence)
 {
+	struct amdgpu_device *adev = pdd->dev->adev;
+	struct amdgpu_vm *vm = drm_priv_to_vm(pdd->drm_priv);
 	bool table_freed = false;
 	uint64_t pte_flags;
 	unsigned long last_start;
@@ -1300,12 +1306,8 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (fence)
 		*fence = dma_fence_get(vm->last_update);
 
-	if (table_freed) {
-		struct kfd_process *p;
-
-		p = container_of(prange->svms, struct kfd_process, svms);
-		amdgpu_amdkfd_flush_gpu_tlb_pasid(adev, p->pasid, TLB_FLUSH_LEGACY);
-	}
+	if (table_freed)
+		kfd_flush_tlb(pdd, TLB_FLUSH_LEGACY);
 out:
 	return r;
 }
@@ -1346,8 +1348,7 @@ svm_range_map_to_gpus(struct svm_range *prange, unsigned long offset,
 			continue;
 		}
 
-		r = svm_range_map_to_gpu(pdd->dev->adev, drm_priv_to_vm(pdd->drm_priv),
-					 prange, offset, npages, readonly,
+		r = svm_range_map_to_gpu(pdd, prange, offset, npages, readonly,
 					 prange->dma_addr[gpuidx],
 					 bo_adev, wait ? &fence : NULL);
 		if (r)
@@ -1643,13 +1644,14 @@ static void svm_range_restore_work(struct work_struct *work)
 
 	pr_debug("restore svm ranges\n");
 
-	/* kfd_process_notifier_release destroys this worker thread. So during
-	 * the lifetime of this thread, kfd_process and mm will be valid.
-	 */
 	p = container_of(svms, struct kfd_process, svms);
-	mm = p->mm;
-	if (!mm)
+
+	/* Keep mm reference when svm_range_validate_and_map ranges */
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		pr_debug("svms 0x%p process mm gone\n", svms);
 		return;
+	}
 
 	svm_range_list_lock_and_flush_work(svms, mm);
 	mutex_lock(&svms->lock);
@@ -1703,6 +1705,7 @@ static void svm_range_restore_work(struct work_struct *work)
 out_reschedule:
 	mutex_unlock(&svms->lock);
 	mmap_write_unlock(mm);
+	mmput(mm);
 
 	/* If validation failed, reschedule another attempt */
 	if (evicted_ranges) {
@@ -1985,10 +1988,9 @@ svm_range_update_notifier_and_interval_tree(struct mm_struct *mm,
 }
 
 static void
-svm_range_handle_list_op(struct svm_range_list *svms, struct svm_range *prange)
+svm_range_handle_list_op(struct svm_range_list *svms, struct svm_range *prange,
+			 struct mm_struct *mm)
 {
-	struct mm_struct *mm = prange->work_item.mm;
-
 	switch (prange->work_item.op) {
 	case SVM_OP_NULL:
 		pr_debug("NULL OP 0x%p prange 0x%p [0x%lx 0x%lx]\n",
@@ -2065,40 +2067,44 @@ static void svm_range_deferred_list_work(struct work_struct *work)
 	struct svm_range_list *svms;
 	struct svm_range *prange;
 	struct mm_struct *mm;
-	struct kfd_process *p;
 
 	svms = container_of(work, struct svm_range_list, deferred_list_work);
 	pr_debug("enter svms 0x%p\n", svms);
 
-	p = container_of(svms, struct kfd_process, svms);
-	/* Avoid mm is gone when inserting mmu notifier */
-	mm = get_task_mm(p->lead_thread);
-	if (!mm) {
-		pr_debug("svms 0x%p process mm gone\n", svms);
-		return;
-	}
-retry:
-	mmap_write_lock(mm);
-
-	/* Checking for the need to drain retry faults must be inside
-	 * mmap write lock to serialize with munmap notifiers.
-	 */
-	if (unlikely(atomic_read(&svms->drain_pagefaults))) {
-		mmap_write_unlock(mm);
-		svm_range_drain_retry_fault(svms);
-		goto retry;
-	}
-
 	spin_lock(&svms->deferred_list_lock);
 	while (!list_empty(&svms->deferred_range_list)) {
 		prange = list_first_entry(&svms->deferred_range_list,
 					  struct svm_range, deferred_list);
-		list_del_init(&prange->deferred_list);
 		spin_unlock(&svms->deferred_list_lock);
 
 		pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange,
 			 prange->start, prange->last, prange->work_item.op);
 
+		mm = prange->work_item.mm;
+retry:
+		mmap_write_lock(mm);
+
+		/* Checking for the need to drain retry faults must be inside
+		 * mmap write lock to serialize with munmap notifiers.
+		 */
+		if (unlikely(atomic_read(&svms->drain_pagefaults))) {
+			mmap_write_unlock(mm);
+			svm_range_drain_retry_fault(svms);
+			goto retry;
+		}
+
+		/* Remove from deferred_list must be inside mmap write lock, for
+		 * two race cases:
+		 * 1. unmap_from_cpu may change work_item.op and add the range
+		 *    to deferred_list again, cause use after free bug.
+		 * 2. svm_range_list_lock_and_flush_work may hold mmap write
+		 *    lock and continue because deferred_list is empty, but
+		 *    deferred_list work is actually waiting for mmap lock.
+		 */
+		spin_lock(&svms->deferred_list_lock);
+		list_del_init(&prange->deferred_list);
+		spin_unlock(&svms->deferred_list_lock);
+
 		mutex_lock(&svms->lock);
 		mutex_lock(&prange->migrate_mutex);
 		while (!list_empty(&prange->child_list)) {
@@ -2109,19 +2115,20 @@ retry:
 			pr_debug("child prange 0x%p op %d\n", pchild,
 				 pchild->work_item.op);
 			list_del_init(&pchild->child_list);
-			svm_range_handle_list_op(svms, pchild);
+			svm_range_handle_list_op(svms, pchild, mm);
 		}
 		mutex_unlock(&prange->migrate_mutex);
 
-		svm_range_handle_list_op(svms, prange);
+		svm_range_handle_list_op(svms, prange, mm);
 		mutex_unlock(&svms->lock);
+		mmap_write_unlock(mm);
+
+		/* Pairs with mmget in svm_range_add_list_work */
+		mmput(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
 	spin_unlock(&svms->deferred_list_lock);
-
-	mmap_write_unlock(mm);
-	mmput(mm);
 	pr_debug("exit svms 0x%p\n", svms);
 }
 
@@ -2139,6 +2146,9 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 			prange->work_item.op = op;
 	} else {
 		prange->work_item.op = op;
+
+		/* Pairs with mmput in deferred_list_work */
+		mmget(mm);
 		prange->work_item.mm = mm;
 		list_add_tail(&prange->deferred_list,
 			      &prange->svms->deferred_range_list);
@@ -2830,6 +2840,8 @@ void svm_range_list_fini(struct kfd_process *p)
 
 	pr_debug("pasid 0x%x svms 0x%p\n", p->pasid, &p->svms);
 
+	cancel_delayed_work_sync(&p->svms.restore_work);
+
 	/* Ensure list work is finished before process is destroyed */
 	flush_work(&p->svms.deferred_list_work);
 
@@ -2840,7 +2852,6 @@ void svm_range_list_fini(struct kfd_process *p)
 	atomic_inc(&p->svms.drain_pagefaults);
 	svm_range_drain_retry_fault(&p->svms);
 
-
 	list_for_each_entry_safe(prange, next, &p->svms.list, list) {
 		svm_range_unlink(prange);
 		svm_range_remove_notifier(prange);
@@ -2865,6 +2876,7 @@ int svm_range_list_init(struct kfd_process *p)
 	INIT_DELAYED_WORK(&svms->restore_work, svm_range_restore_work);
 	INIT_WORK(&svms->deferred_list_work, svm_range_deferred_list_work);
 	INIT_LIST_HEAD(&svms->deferred_range_list);
+	INIT_LIST_HEAD(&svms->criu_svm_metadata_list);
 	spin_lock_init(&svms->deferred_list_lock);
 
 	for (i = 0; i < p->n_pdds; i++)
@@ -3193,10 +3205,10 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 }
 
 static int
-svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size,
-		   uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs)
+svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm,
+		   uint64_t start, uint64_t size, uint32_t nattr,
+		   struct kfd_ioctl_svm_attribute *attrs)
 {
-	struct mm_struct *mm = current->mm;
 	struct list_head update_list;
 	struct list_head insert_list;
 	struct list_head remove_list;
@@ -3295,8 +3307,9 @@ out:
 }
 
 static int
-svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
-		   uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs)
+svm_range_get_attr(struct kfd_process *p, struct mm_struct *mm,
+		   uint64_t start, uint64_t size, uint32_t nattr,
+		   struct kfd_ioctl_svm_attribute *attrs)
 {
 	DECLARE_BITMAP(bitmap_access, MAX_GPU_INSTANCE);
 	DECLARE_BITMAP(bitmap_aip, MAX_GPU_INSTANCE);
@@ -3306,7 +3319,6 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 	bool get_accessible = false;
 	bool get_flags = false;
 	uint64_t last = start + size - 1UL;
-	struct mm_struct *mm = current->mm;
 	uint8_t granularity = 0xff;
 	struct interval_tree_node *node;
 	struct svm_range_list *svms;
@@ -3471,10 +3483,321 @@ fill_values:
 	return 0;
 }
 
+int kfd_criu_resume_svm(struct kfd_process *p)
+{
+	struct kfd_ioctl_svm_attribute *set_attr_new, *set_attr = NULL;
+	int nattr_common = 4, nattr_accessibility = 1;
+	struct criu_svm_metadata *criu_svm_md = NULL;
+	struct svm_range_list *svms = &p->svms;
+	struct criu_svm_metadata *next = NULL;
+	uint32_t set_flags = 0xffffffff;
+	int i, j, num_attrs, ret = 0;
+	uint64_t set_attr_size;
+	struct mm_struct *mm;
+
+	if (list_empty(&svms->criu_svm_metadata_list)) {
+		pr_debug("No SVM data from CRIU restore stage 2\n");
+		return ret;
+	}
+
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		pr_err("failed to get mm for the target process\n");
+		return -ESRCH;
+	}
+
+	num_attrs = nattr_common + (nattr_accessibility * p->n_pdds);
+
+	i = j = 0;
+	list_for_each_entry(criu_svm_md, &svms->criu_svm_metadata_list, list) {
+		pr_debug("criu_svm_md[%d]\n\tstart: 0x%llx size: 0x%llx (npages)\n",
+			 i, criu_svm_md->data.start_addr, criu_svm_md->data.size);
+
+		for (j = 0; j < num_attrs; j++) {
+			pr_debug("\ncriu_svm_md[%d]->attrs[%d].type : 0x%x\ncriu_svm_md[%d]->attrs[%d].value : 0x%x\n",
+				 i, j, criu_svm_md->data.attrs[j].type,
+				 i, j, criu_svm_md->data.attrs[j].value);
+			switch (criu_svm_md->data.attrs[j].type) {
+			/* During Checkpoint operation, the query for
+			 * KFD_IOCTL_SVM_ATTR_PREFETCH_LOC attribute might
+			 * return KFD_IOCTL_SVM_LOCATION_UNDEFINED if they were
+			 * not used by the range which was checkpointed. Care
+			 * must be taken to not restore with an invalid value
+			 * otherwise the gpuidx value will be invalid and
+			 * set_attr would eventually fail so just replace those
+			 * with another dummy attribute such as
+			 * KFD_IOCTL_SVM_ATTR_SET_FLAGS.
+			 */
+			case KFD_IOCTL_SVM_ATTR_PREFETCH_LOC:
+				if (criu_svm_md->data.attrs[j].value ==
+				    KFD_IOCTL_SVM_LOCATION_UNDEFINED) {
+					criu_svm_md->data.attrs[j].type =
+						KFD_IOCTL_SVM_ATTR_SET_FLAGS;
+					criu_svm_md->data.attrs[j].value = 0;
+				}
+				break;
+			case KFD_IOCTL_SVM_ATTR_SET_FLAGS:
+				set_flags = criu_svm_md->data.attrs[j].value;
+				break;
+			default:
+				break;
+			}
+		}
+
+		/* CLR_FLAGS is not available via get_attr during checkpoint but
+		 * it needs to be inserted before restoring the ranges so
+		 * allocate extra space for it before calling set_attr
+		 */
+		set_attr_size = sizeof(struct kfd_ioctl_svm_attribute) *
+						(num_attrs + 1);
+		set_attr_new = krealloc(set_attr, set_attr_size,
+					    GFP_KERNEL);
+		if (!set_attr_new) {
+			ret = -ENOMEM;
+			goto exit;
+		}
+		set_attr = set_attr_new;
+
+		memcpy(set_attr, criu_svm_md->data.attrs, num_attrs *
+					sizeof(struct kfd_ioctl_svm_attribute));
+		set_attr[num_attrs].type = KFD_IOCTL_SVM_ATTR_CLR_FLAGS;
+		set_attr[num_attrs].value = ~set_flags;
+
+		ret = svm_range_set_attr(p, mm, criu_svm_md->data.start_addr,
+					 criu_svm_md->data.size, num_attrs + 1,
+					 set_attr);
+		if (ret) {
+			pr_err("CRIU: failed to set range attributes\n");
+			goto exit;
+		}
+
+		i++;
+	}
+exit:
+	kfree(set_attr);
+	list_for_each_entry_safe(criu_svm_md, next, &svms->criu_svm_metadata_list, list) {
+		pr_debug("freeing criu_svm_md[]\n\tstart: 0x%llx\n",
+						criu_svm_md->data.start_addr);
+		kfree(criu_svm_md);
+	}
+
+	mmput(mm);
+	return ret;
+
+}
+
+int kfd_criu_restore_svm(struct kfd_process *p,
+			 uint8_t __user *user_priv_ptr,
+			 uint64_t *priv_data_offset,
+			 uint64_t max_priv_data_size)
+{
+	uint64_t svm_priv_data_size, svm_object_md_size, svm_attrs_size;
+	int nattr_common = 4, nattr_accessibility = 1;
+	struct criu_svm_metadata *criu_svm_md = NULL;
+	struct svm_range_list *svms = &p->svms;
+	uint32_t num_devices;
+	int ret = 0;
+
+	num_devices = p->n_pdds;
+	/* Handle one SVM range object at a time, also the number of gpus are
+	 * assumed to be same on the restore node, checking must be done while
+	 * evaluating the topology earlier
+	 */
+
+	svm_attrs_size = sizeof(struct kfd_ioctl_svm_attribute) *
+		(nattr_common + nattr_accessibility * num_devices);
+	svm_object_md_size = sizeof(struct criu_svm_metadata) + svm_attrs_size;
+
+	svm_priv_data_size = sizeof(struct kfd_criu_svm_range_priv_data) +
+								svm_attrs_size;
+
+	criu_svm_md = kzalloc(svm_object_md_size, GFP_KERNEL);
+	if (!criu_svm_md) {
+		pr_err("failed to allocate memory to store svm metadata\n");
+		return -ENOMEM;
+	}
+	if (*priv_data_offset + svm_priv_data_size > max_priv_data_size) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	ret = copy_from_user(&criu_svm_md->data, user_priv_ptr + *priv_data_offset,
+			     svm_priv_data_size);
+	if (ret) {
+		ret = -EFAULT;
+		goto exit;
+	}
+	*priv_data_offset += svm_priv_data_size;
+
+	list_add_tail(&criu_svm_md->list, &svms->criu_svm_metadata_list);
+
+	return 0;
+
+
+exit:
+	kfree(criu_svm_md);
+	return ret;
+}
+
+int svm_range_get_info(struct kfd_process *p, uint32_t *num_svm_ranges,
+		       uint64_t *svm_priv_data_size)
+{
+	uint64_t total_size, accessibility_size, common_attr_size;
+	int nattr_common = 4, nattr_accessibility = 1;
+	int num_devices = p->n_pdds;
+	struct svm_range_list *svms;
+	struct svm_range *prange;
+	uint32_t count = 0;
+
+	*svm_priv_data_size = 0;
+
+	svms = &p->svms;
+	if (!svms)
+		return -EINVAL;
+
+	mutex_lock(&svms->lock);
+	list_for_each_entry(prange, &svms->list, list) {
+		pr_debug("prange: 0x%p start: 0x%lx\t npages: 0x%llx\t end: 0x%llx\n",
+			 prange, prange->start, prange->npages,
+			 prange->start + prange->npages - 1);
+		count++;
+	}
+	mutex_unlock(&svms->lock);
+
+	*num_svm_ranges = count;
+	/* Only the accessbility attributes need to be queried for all the gpus
+	 * individually, remaining ones are spanned across the entire process
+	 * regardless of the various gpu nodes. Of the remaining attributes,
+	 * KFD_IOCTL_SVM_ATTR_CLR_FLAGS need not be saved.
+	 *
+	 * KFD_IOCTL_SVM_ATTR_PREFERRED_LOC
+	 * KFD_IOCTL_SVM_ATTR_PREFETCH_LOC
+	 * KFD_IOCTL_SVM_ATTR_SET_FLAGS
+	 * KFD_IOCTL_SVM_ATTR_GRANULARITY
+	 *
+	 * ** ACCESSBILITY ATTRIBUTES **
+	 * (Considered as one, type is altered during query, value is gpuid)
+	 * KFD_IOCTL_SVM_ATTR_ACCESS
+	 * KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE
+	 * KFD_IOCTL_SVM_ATTR_NO_ACCESS
+	 */
+	if (*num_svm_ranges > 0) {
+		common_attr_size = sizeof(struct kfd_ioctl_svm_attribute) *
+			nattr_common;
+		accessibility_size = sizeof(struct kfd_ioctl_svm_attribute) *
+			nattr_accessibility * num_devices;
+
+		total_size = sizeof(struct kfd_criu_svm_range_priv_data) +
+			common_attr_size + accessibility_size;
+
+		*svm_priv_data_size = *num_svm_ranges * total_size;
+	}
+
+	pr_debug("num_svm_ranges %u total_priv_size %llu\n", *num_svm_ranges,
+		 *svm_priv_data_size);
+	return 0;
+}
+
+int kfd_criu_checkpoint_svm(struct kfd_process *p,
+			    uint8_t __user *user_priv_data,
+			    uint64_t *priv_data_offset)
+{
+	struct kfd_criu_svm_range_priv_data *svm_priv = NULL;
+	struct kfd_ioctl_svm_attribute *query_attr = NULL;
+	uint64_t svm_priv_data_size, query_attr_size = 0;
+	int index, nattr_common = 4, ret = 0;
+	struct svm_range_list *svms;
+	int num_devices = p->n_pdds;
+	struct svm_range *prange;
+	struct mm_struct *mm;
+
+	svms = &p->svms;
+	if (!svms)
+		return -EINVAL;
+
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		pr_err("failed to get mm for the target process\n");
+		return -ESRCH;
+	}
+
+	query_attr_size = sizeof(struct kfd_ioctl_svm_attribute) *
+				(nattr_common + num_devices);
+
+	query_attr = kzalloc(query_attr_size, GFP_KERNEL);
+	if (!query_attr) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	query_attr[0].type = KFD_IOCTL_SVM_ATTR_PREFERRED_LOC;
+	query_attr[1].type = KFD_IOCTL_SVM_ATTR_PREFETCH_LOC;
+	query_attr[2].type = KFD_IOCTL_SVM_ATTR_SET_FLAGS;
+	query_attr[3].type = KFD_IOCTL_SVM_ATTR_GRANULARITY;
+
+	for (index = 0; index < num_devices; index++) {
+		struct kfd_process_device *pdd = p->pdds[index];
+
+		query_attr[index + nattr_common].type =
+			KFD_IOCTL_SVM_ATTR_ACCESS;
+		query_attr[index + nattr_common].value = pdd->user_gpu_id;
+	}
+
+	svm_priv_data_size = sizeof(*svm_priv) + query_attr_size;
+
+	svm_priv = kzalloc(svm_priv_data_size, GFP_KERNEL);
+	if (!svm_priv) {
+		ret = -ENOMEM;
+		goto exit_query;
+	}
+
+	index = 0;
+	list_for_each_entry(prange, &svms->list, list) {
+
+		svm_priv->object_type = KFD_CRIU_OBJECT_TYPE_SVM_RANGE;
+		svm_priv->start_addr = prange->start;
+		svm_priv->size = prange->npages;
+		memcpy(&svm_priv->attrs, query_attr, query_attr_size);
+		pr_debug("CRIU: prange: 0x%p start: 0x%lx\t npages: 0x%llx end: 0x%llx\t size: 0x%llx\n",
+			 prange, prange->start, prange->npages,
+			 prange->start + prange->npages - 1,
+			 prange->npages * PAGE_SIZE);
+
+		ret = svm_range_get_attr(p, mm, svm_priv->start_addr,
+					 svm_priv->size,
+					 (nattr_common + num_devices),
+					 svm_priv->attrs);
+		if (ret) {
+			pr_err("CRIU: failed to obtain range attributes\n");
+			goto exit_priv;
+		}
+
+		if (copy_to_user(user_priv_data + *priv_data_offset, svm_priv,
+				 svm_priv_data_size)) {
+			pr_err("Failed to copy svm priv to user\n");
+			ret = -EFAULT;
+			goto exit_priv;
+		}
+
+		*priv_data_offset += svm_priv_data_size;
+
+	}
+
+
+exit_priv:
+	kfree(svm_priv);
+exit_query:
+	kfree(query_attr);
+exit:
+	mmput(mm);
+	return ret;
+}
+
 int
 svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
 	  uint64_t size, uint32_t nattrs, struct kfd_ioctl_svm_attribute *attrs)
 {
+	struct mm_struct *mm = current->mm;
 	int r;
 
 	start >>= PAGE_SHIFT;
@@ -3482,10 +3805,10 @@ svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
 
 	switch (op) {
 	case KFD_IOCTL_SVM_OP_SET_ATTR:
-		r = svm_range_set_attr(p, start, size, nattrs, attrs);
+		r = svm_range_set_attr(p, mm, start, size, nattrs, attrs);
 		break;
 	case KFD_IOCTL_SVM_OP_GET_ATTR:
-		r = svm_range_get_attr(p, start, size, nattrs, attrs);
+		r = svm_range_get_attr(p, mm, start, size, nattrs, attrs);
 		break;
 	default:
 		r = EINVAL;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 949b477e2f4c..66c77f00ac3e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -183,6 +183,16 @@ void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 void svm_range_free_dma_mappings(struct svm_range *prange);
 void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
 			void *owner);
+int svm_range_get_info(struct kfd_process *p, uint32_t *num_svm_ranges,
+		       uint64_t *svm_priv_data_size);
+int kfd_criu_checkpoint_svm(struct kfd_process *p,
+			    uint8_t __user *user_priv_data,
+			    uint64_t *priv_offset);
+int kfd_criu_restore_svm(struct kfd_process *p,
+			 uint8_t __user *user_priv_ptr,
+			 uint64_t *priv_data_offset,
+			 uint64_t max_priv_data_size);
+int kfd_criu_resume_svm(struct kfd_process *p);
 struct kfd_process_device *
 svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
 void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_struct *mm);
@@ -220,6 +230,35 @@ static inline int svm_range_schedule_evict_svm_bo(
 	return -EINVAL;
 }
 
+static inline int svm_range_get_info(struct kfd_process *p,
+				     uint32_t *num_svm_ranges,
+				     uint64_t *svm_priv_data_size)
+{
+	*num_svm_ranges = 0;
+	*svm_priv_data_size = 0;
+	return 0;
+}
+
+static inline int kfd_criu_checkpoint_svm(struct kfd_process *p,
+					  uint8_t __user *user_priv_data,
+					  uint64_t *priv_offset)
+{
+	return 0;
+}
+
+static inline int kfd_criu_restore_svm(struct kfd_process *p,
+				       uint8_t __user *user_priv_ptr,
+				       uint64_t *priv_data_offset,
+				       uint64_t max_priv_data_size)
+{
+	return -EINVAL;
+}
+
+static inline int kfd_criu_resume_svm(struct kfd_process *p)
+{
+	return 0;
+}
+
 #define KFD_IS_SVM_API_SUPPORTED(dev) false
 
 #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */