Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

25 files changed, 2538 insertions, 326 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index bc5a2945bd2b..ed2f06c9f346 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -4,6 +4,7 @@
 
 config HSA_AMD
 	tristate "HSA kernel driver for AMD GPU devices"
-	depends on DRM_AMDGPU && AMD_IOMMU_V2 && X86_64
+	depends on DRM_AMDGPU && X86_64
+	imply AMD_IOMMU_V2
 	help
 	  Enable this if you want to use HSA features on AMD GPU devices.
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index a317e76ffb5e..0d0242240c47 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -37,6 +37,10 @@ amdkfd-y	:= kfd_module.o kfd_device.o kfd_chardev.o kfd_topology.o \
 		kfd_interrupt.o kfd_events.o cik_event_interrupt.o \
 		kfd_dbgdev.o kfd_dbgmgr.o kfd_crat.o
 
+ifneq ($(CONFIG_AMD_IOMMU_V2),)
+amdkfd-y += kfd_iommu.o
+endif
+
 amdkfd-$(CONFIG_DEBUG_FS) += kfd_debugfs.o
 
 obj-$(CONFIG_HSA_AMD)	+= amdkfd.o
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 62c3d9cd6ef1..cd679cf1fd30 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/fs.h>
+#include <linux/file.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -825,12 +826,155 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 	return 0;
 }
 
+static int kfd_ioctl_get_process_apertures_new(struct file *filp,
+				struct kfd_process *p, void *data)
+{
+	struct kfd_ioctl_get_process_apertures_new_args *args = data;
+	struct kfd_process_device_apertures *pa;
+	struct kfd_process_device *pdd;
+	uint32_t nodes = 0;
+	int ret;
+
+	dev_dbg(kfd_device, "get apertures for PASID %d", p->pasid);
+
+	if (args->num_of_nodes == 0) {
+		/* Return number of nodes, so that user space can alloacate
+		 * sufficient memory
+		 */
+		mutex_lock(&p->mutex);
+
+		if (!kfd_has_process_device_data(p))
+			goto out_unlock;
+
+		/* Run over all pdd of the process */
+		pdd = kfd_get_first_process_device_data(p);
+		do {
+			args->num_of_nodes++;
+			pdd = kfd_get_next_process_device_data(p, pdd);
+		} while (pdd);
+
+		goto out_unlock;
+	}
+
+	/* Fill in process-aperture information for all available
+	 * nodes, but not more than args->num_of_nodes as that is
+	 * the amount of memory allocated by user
+	 */
+	pa = kzalloc((sizeof(struct kfd_process_device_apertures) *
+				args->num_of_nodes), GFP_KERNEL);
+	if (!pa)
+		return -ENOMEM;
+
+	mutex_lock(&p->mutex);
+
+	if (!kfd_has_process_device_data(p)) {
+		args->num_of_nodes = 0;
+		kfree(pa);
+		goto out_unlock;
+	}
+
+	/* Run over all pdd of the process */
+	pdd = kfd_get_first_process_device_data(p);
+	do {
+		pa[nodes].gpu_id = pdd->dev->id;
+		pa[nodes].lds_base = pdd->lds_base;
+		pa[nodes].lds_limit = pdd->lds_limit;
+		pa[nodes].gpuvm_base = pdd->gpuvm_base;
+		pa[nodes].gpuvm_limit = pdd->gpuvm_limit;
+		pa[nodes].scratch_base = pdd->scratch_base;
+		pa[nodes].scratch_limit = pdd->scratch_limit;
+
+		dev_dbg(kfd_device,
+			"gpu id %u\n", pdd->dev->id);
+		dev_dbg(kfd_device,
+			"lds_base %llX\n", pdd->lds_base);
+		dev_dbg(kfd_device,
+			"lds_limit %llX\n", pdd->lds_limit);
+		dev_dbg(kfd_device,
+			"gpuvm_base %llX\n", pdd->gpuvm_base);
+		dev_dbg(kfd_device,
+			"gpuvm_limit %llX\n", pdd->gpuvm_limit);
+		dev_dbg(kfd_device,
+			"scratch_base %llX\n", pdd->scratch_base);
+		dev_dbg(kfd_device,
+			"scratch_limit %llX\n", pdd->scratch_limit);
+		nodes++;
+
+		pdd = kfd_get_next_process_device_data(p, pdd);
+	} while (pdd && (nodes < args->num_of_nodes));
+	mutex_unlock(&p->mutex);
+
+	args->num_of_nodes = nodes;
+	ret = copy_to_user(
+			(void __user *)args->kfd_process_device_apertures_ptr,
+			pa,
+			(nodes * sizeof(struct kfd_process_device_apertures)));
+	kfree(pa);
+	return ret ? -EFAULT : 0;
+
+out_unlock:
+	mutex_unlock(&p->mutex);
+	return 0;
+}
+
 static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 					void *data)
 {
 	struct kfd_ioctl_create_event_args *args = data;
 	int err;
 
+	/* For dGPUs the event page is allocated in user mode. The
+	 * handle is passed to KFD with the first call to this IOCTL
+	 * 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;
+
+		if (p->signal_page) {
+			pr_err("Event page is already set\n");
+			return -EINVAL;
+		}
+
+		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);
+		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;
+		}
+		mutex_unlock(&p->mutex);
+
+		err = kfd->kfd2kgd->map_gtt_bo_to_kernel(kfd->kgd,
+						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);
+		if (err) {
+			pr_err("Failed to set event page\n");
+			return err;
+		}
+	}
+
 	err = kfd_event_create(filp, p, args->event_type,
 				args->auto_reset != 0, args->node_id,
 				&args->event_id, &args->event_trigger_data,
@@ -838,6 +982,10 @@ static int kfd_ioctl_create_event(struct file *filp, struct kfd_process *p,
 				&args->event_slot_index);
 
 	return err;
+
+out_unlock:
+	mutex_unlock(&p->mutex);
+	return err;
 }
 
 static int kfd_ioctl_destroy_event(struct file *filp, struct kfd_process *p,
@@ -901,7 +1049,8 @@ static int kfd_ioctl_set_scratch_backing_va(struct file *filep,
 
 	mutex_unlock(&p->mutex);
 
-	if (sched_policy == KFD_SCHED_POLICY_NO_HWS && pdd->qpd.vmid != 0)
+	if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS &&
+	    pdd->qpd.vmid != 0)
 		dev->kfd2kgd->set_scratch_backing_va(
 			dev->kgd, args->va_addr, pdd->qpd.vmid);
 
@@ -954,6 +1103,371 @@ static int kfd_ioctl_get_tile_config(struct file *filep,
 	return 0;
 }
 
+static int kfd_ioctl_acquire_vm(struct file *filep, struct kfd_process *p,
+				void *data)
+{
+	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);
+	if (!pdd) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	if (pdd->drm_file) {
+		ret = pdd->drm_file == drm_file ? 0 : -EBUSY;
+		goto err_unlock;
+	}
+
+	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:
+	mutex_unlock(&p->mutex);
+	fput(drm_file);
+	return ret;
+}
+
+bool kfd_dev_is_large_bar(struct kfd_dev *dev)
+{
+	struct kfd_local_mem_info mem_info;
+
+	if (debug_largebar) {
+		pr_debug("Simulate large-bar allocation on non large-bar machine\n");
+		return true;
+	}
+
+	if (dev->device_info->needs_iommu_device)
+		return false;
+
+	dev->kfd2kgd->get_local_mem_info(dev->kgd, &mem_info);
+	if (mem_info.local_mem_size_private == 0 &&
+			mem_info.local_mem_size_public > 0)
+		return true;
+	return false;
+}
+
+static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
+					struct kfd_process *p, void *data)
+{
+	struct kfd_ioctl_alloc_memory_of_gpu_args *args = data;
+	struct kfd_process_device *pdd;
+	void *mem;
+	struct kfd_dev *dev;
+	int idr_handle;
+	long err;
+	uint64_t offset = args->mmap_offset;
+	uint32_t flags = args->flags;
+
+	if (args->size == 0)
+		return -EINVAL;
+
+	dev = kfd_device_by_id(args->gpu_id);
+	if (!dev)
+		return -EINVAL;
+
+	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;
+	}
+
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_bind_process_to_device(dev, p);
+	if (IS_ERR(pdd)) {
+		err = PTR_ERR(pdd);
+		goto err_unlock;
+	}
+
+	err = dev->kfd2kgd->alloc_memory_of_gpu(
+		dev->kgd, args->va_addr, args->size,
+		pdd->vm, (struct kgd_mem **) &mem, &offset,
+		flags);
+
+	if (err)
+		goto err_unlock;
+
+	idr_handle = kfd_process_device_create_obj_handle(pdd, mem);
+	if (idr_handle < 0) {
+		err = -EFAULT;
+		goto err_free;
+	}
+
+	mutex_unlock(&p->mutex);
+
+	args->handle = MAKE_HANDLE(args->gpu_id, idr_handle);
+	args->mmap_offset = offset;
+
+	return 0;
+
+err_free:
+	dev->kfd2kgd->free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem);
+err_unlock:
+	mutex_unlock(&p->mutex);
+	return err;
+}
+
+static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
+					struct kfd_process *p, void *data)
+{
+	struct kfd_ioctl_free_memory_of_gpu_args *args = data;
+	struct kfd_process_device *pdd;
+	void *mem;
+	struct kfd_dev *dev;
+	int ret;
+
+	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
+	if (!dev)
+		return -EINVAL;
+
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_get_process_device_data(dev, p);
+	if (!pdd) {
+		pr_err("Process device data doesn't exist\n");
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	mem = kfd_process_device_translate_handle(
+		pdd, GET_IDR_HANDLE(args->handle));
+	if (!mem) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	ret = dev->kfd2kgd->free_memory_of_gpu(dev->kgd, (struct kgd_mem *)mem);
+
+	/* If freeing the buffer failed, leave the handle in place for
+	 * clean-up during process tear-down.
+	 */
+	if (!ret)
+		kfd_process_device_remove_obj_handle(
+			pdd, GET_IDR_HANDLE(args->handle));
+
+err_unlock:
+	mutex_unlock(&p->mutex);
+	return ret;
+}
+
+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;
+	long err = 0;
+	int i;
+	uint32_t *devices_arr = NULL;
+
+	dev = kfd_device_by_id(GET_GPU_ID(args->handle));
+	if (!dev)
+		return -EINVAL;
+
+	if (!args->n_devices) {
+		pr_debug("Device IDs array empty\n");
+		return -EINVAL;
+	}
+	if (args->n_success > args->n_devices) {
+		pr_debug("n_success exceeds n_devices\n");
+		return -EINVAL;
+	}
+
+	devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr),
+			      GFP_KERNEL);
+	if (!devices_arr)
+		return -ENOMEM;
+
+	err = copy_from_user(devices_arr,
+			     (void __user *)args->device_ids_array_ptr,
+			     args->n_devices * sizeof(*devices_arr));
+	if (err != 0) {
+		err = -EFAULT;
+		goto copy_from_user_failed;
+	}
+
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_bind_process_to_device(dev, p);
+	if (IS_ERR(pdd)) {
+		err = PTR_ERR(pdd);
+		goto bind_process_to_device_failed;
+	}
+
+	mem = kfd_process_device_translate_handle(pdd,
+						GET_IDR_HANDLE(args->handle));
+	if (!mem) {
+		err = -ENOMEM;
+		goto get_mem_obj_from_handle_failed;
+	}
+
+	for (i = args->n_success; i < args->n_devices; i++) {
+		peer = kfd_device_by_id(devices_arr[i]);
+		if (!peer) {
+			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);
+		if (IS_ERR(peer_pdd)) {
+			err = PTR_ERR(peer_pdd);
+			goto get_mem_obj_from_handle_failed;
+		}
+		err = peer->kfd2kgd->map_memory_to_gpu(
+			peer->kgd, (struct kgd_mem *)mem, peer_pdd->vm);
+		if (err) {
+			pr_err("Failed to map to gpu %d/%d\n",
+			       i, args->n_devices);
+			goto map_memory_to_gpu_failed;
+		}
+		args->n_success = i+1;
+	}
+
+	mutex_unlock(&p->mutex);
+
+	err = dev->kfd2kgd->sync_memory(dev->kgd, (struct kgd_mem *) mem, true);
+	if (err) {
+		pr_debug("Sync memory failed, wait interrupted by user signal\n");
+		goto sync_memory_failed;
+	}
+
+	/* 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);
+		if (WARN_ON_ONCE(!peer_pdd))
+			continue;
+		kfd_flush_tlb(peer_pdd);
+	}
+
+	kfree(devices_arr);
+
+	return err;
+
+bind_process_to_device_failed:
+get_mem_obj_from_handle_failed:
+map_memory_to_gpu_failed:
+	mutex_unlock(&p->mutex);
+copy_from_user_failed:
+sync_memory_failed:
+	kfree(devices_arr);
+
+	return err;
+}
+
+static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
+					struct kfd_process *p, void *data)
+{
+	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;
+	}
+	if (args->n_success > args->n_devices) {
+		pr_debug("n_success exceeds n_devices\n");
+		return -EINVAL;
+	}
+
+	devices_arr = kmalloc(args->n_devices * sizeof(*devices_arr),
+			      GFP_KERNEL);
+	if (!devices_arr)
+		return -ENOMEM;
+
+	err = copy_from_user(devices_arr,
+			     (void __user *)args->device_ids_array_ptr,
+			     args->n_devices * sizeof(*devices_arr));
+	if (err != 0) {
+		err = -EFAULT;
+		goto copy_from_user_failed;
+	}
+
+	mutex_lock(&p->mutex);
+
+	pdd = kfd_get_process_device_data(dev, p);
+	if (!pdd) {
+		err = PTR_ERR(pdd);
+		goto bind_process_to_device_failed;
+	}
+
+	mem = kfd_process_device_translate_handle(pdd,
+						GET_IDR_HANDLE(args->handle));
+	if (!mem) {
+		err = -ENOMEM;
+		goto get_mem_obj_from_handle_failed;
+	}
+
+	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);
+		if (!peer_pdd) {
+			err = -ENODEV;
+			goto get_mem_obj_from_handle_failed;
+		}
+		err = dev->kfd2kgd->unmap_memory_to_gpu(
+			peer->kgd, (struct kgd_mem *)mem, peer_pdd->vm);
+		if (err) {
+			pr_err("Failed to unmap from gpu %d/%d\n",
+			       i, args->n_devices);
+			goto unmap_memory_from_gpu_failed;
+		}
+		args->n_success = i+1;
+	}
+	kfree(devices_arr);
+
+	mutex_unlock(&p->mutex);
+
+	return 0;
+
+bind_process_to_device_failed:
+get_mem_obj_from_handle_failed:
+unmap_memory_from_gpu_failed:
+	mutex_unlock(&p->mutex);
+copy_from_user_failed:
+	kfree(devices_arr);
+	return err;
+}
+
 #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
 	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \
 			    .cmd_drv = 0, .name = #ioctl}
@@ -1016,6 +1530,25 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_TRAP_HANDLER,
 			kfd_ioctl_set_trap_handler, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_PROCESS_APERTURES_NEW,
+			kfd_ioctl_get_process_apertures_new, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_ACQUIRE_VM,
+			kfd_ioctl_acquire_vm, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_MEMORY_OF_GPU,
+			kfd_ioctl_alloc_memory_of_gpu, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_FREE_MEMORY_OF_GPU,
+			kfd_ioctl_free_memory_of_gpu, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_MAP_MEMORY_TO_GPU,
+			kfd_ioctl_map_memory_to_gpu, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU,
+			kfd_ioctl_unmap_memory_from_gpu, 0),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 2bc2816767a7..4f126ef6139b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -22,10 +22,10 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
-#include <linux/amd-iommu.h>
 #include "kfd_crat.h"
 #include "kfd_priv.h"
 #include "kfd_topology.h"
+#include "kfd_iommu.h"
 
 /* GPU Processor ID base for dGPUs for which VCRAT needs to be created.
  * GPU processor ID are expressed with Bit[31]=1.
@@ -882,7 +882,7 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
 	crat_table->length = sizeof(struct crat_header);
 
 	status = acpi_get_table("DSDT", 0, &acpi_table);
-	if (status == AE_NOT_FOUND)
+	if (status != AE_OK)
 		pr_warn("DSDT table not found for OEM information\n");
 	else {
 		crat_table->oem_revision = acpi_table->revision;
@@ -1037,15 +1037,11 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	struct crat_subtype_generic *sub_type_hdr;
 	struct crat_subtype_computeunit *cu;
 	struct kfd_cu_info cu_info;
-	struct amd_iommu_device_info iommu_info;
 	int avail_size = *size;
 	uint32_t total_num_of_cu;
 	int num_of_cache_entries = 0;
 	int cache_mem_filled = 0;
 	int ret = 0;
-	const u32 required_iommu_flags = AMD_IOMMU_DEVICE_FLAG_ATS_SUP |
-					 AMD_IOMMU_DEVICE_FLAG_PRI_SUP |
-					 AMD_IOMMU_DEVICE_FLAG_PASID_SUP;
 	struct kfd_local_mem_info local_mem_info;
 
 	if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_GPU)
@@ -1106,12 +1102,8 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	/* Check if this node supports IOMMU. During parsing this flag will
 	 * translate to HSA_CAP_ATS_PRESENT
 	 */
-	iommu_info.flags = 0;
-	if (amd_iommu_device_info(kdev->pdev, &iommu_info) == 0) {
-		if ((iommu_info.flags & required_iommu_flags) ==
-				required_iommu_flags)
-			cu->hsa_capability |= CRAT_CU_FLAGS_IOMMU_PRESENT;
-	}
+	if (!kfd_iommu_check_device(kdev))
+		cu->hsa_capability |= CRAT_CU_FLAGS_IOMMU_PRESENT;
 
 	crat_table->length += sub_type_hdr->length;
 	crat_table->total_entries++;
@@ -1125,6 +1117,9 @@ static int kfd_create_vcrat_image_gpu(void *pcrat_image,
 	sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
 			sub_type_hdr->length);
 
+	if (debug_largebar)
+		local_mem_info.local_mem_size_private = 0;
+
 	if (local_mem_info.local_mem_size_private == 0)
 		ret = kfd_fill_gpu_memory_affinity(&avail_size,
 				kdev, HSA_MEM_HEAP_TYPE_FB_PUBLIC,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
index 3da25f7bda6b..9d4af961c5d1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
@@ -33,6 +33,7 @@
 #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);
 
@@ -83,7 +84,7 @@ bool kfd_dbgmgr_create(struct kfd_dbgmgr **ppmgr, struct kfd_dev *pdev)
 	}
 
 	/* get actual type of DBGDevice cpsch or not */
-	if (sched_policy == KFD_SCHED_POLICY_NO_HWS)
+	if (pdev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS)
 		type = DBGDEV_TYPE_NODIQ;
 
 	kfd_dbgdev_init(new_buff->dbgdev, pdev, type);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index a8fa33a08de3..3346699960dd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -20,7 +20,9 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#if defined(CONFIG_AMD_IOMMU_V2_MODULE) || defined(CONFIG_AMD_IOMMU_V2)
 #include <linux/amd-iommu.h>
+#endif
 #include <linux/bsearch.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
@@ -28,9 +30,12 @@
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_vi.h"
 #include "cwsr_trap_handler_gfx8.asm"
+#include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
+static atomic_t kfd_device_suspended = ATOMIC_INIT(0);
 
+#ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
 	.asic_family = CHIP_KAVERI,
 	.max_pasid_bits = 16,
@@ -41,6 +46,8 @@ static const struct kfd_device_info kaveri_device_info = {
 	.num_of_watch_points = 4,
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.supports_cwsr = false,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = false,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -53,15 +60,125 @@ static const struct kfd_device_info carrizo_device_info = {
 	.num_of_watch_points = 4,
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.supports_cwsr = true,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = false,
 };
+#endif
+
+static const struct kfd_device_info hawaii_device_info = {
+	.asic_family = CHIP_HAWAII,
+	.max_pasid_bits = 16,
+	/* max num of queues for KV.TODO should be a dynamic value */
+	.max_no_of_hqd	= 24,
+	.ih_ring_entry_size = 4 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_cik,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = false,
+	.needs_iommu_device = false,
+	.needs_pci_atomics = false,
+};
+
+static const struct kfd_device_info tonga_device_info = {
+	.asic_family = CHIP_TONGA,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.ih_ring_entry_size = 4 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_cik,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = false,
+	.needs_iommu_device = false,
+	.needs_pci_atomics = true,
+};
+
+static const struct kfd_device_info tonga_vf_device_info = {
+	.asic_family = CHIP_TONGA,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.ih_ring_entry_size = 4 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_cik,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = false,
+	.needs_iommu_device = false,
+	.needs_pci_atomics = false,
+};
+
+static const struct kfd_device_info fiji_device_info = {
+	.asic_family = CHIP_FIJI,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.ih_ring_entry_size = 4 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_cik,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cws