Merge tag 'drm-amdkfd-next-2018-07-28' of git://people.freedesktop.org/~gabbayo/linux into drm-next

This is amdkfd pull for 4.19. The major changes are:

- Add Raven support. Raven refers to Ryzen APUs with integrated GFXv9 GPU.
- Integrate GPU reset support

In addition, there are a couple of small fixes and improvements, such as:

- Better handling and reporting to user of VM faults
- Fix race upon context restore
- Allow the user to use specific Compute Units
- Basic power management
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180728122306.GA5235@ogabbay-vm

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -243,6 +243,33 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 	return r;
 }
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->pre_reset(adev->kfd);
+
+	return r;
+}
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->post_reset(adev->kfd);
+
+	return r;
+}
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_device_gpu_recover(adev, NULL, false);
+}
+
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
@@ -461,6 +488,14 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 	return ret;
 }
 
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE, !idle);
+}
+
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 {
 	if (adev->kfd) {

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -119,6 +119,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len);
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
@@ -126,6 +127,12 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
+
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
@@ -183,6 +190,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *info);
+
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

@@ -145,6 +145,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t page_table_base);
 static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
 static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd);
 
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
@@ -216,6 +217,10 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
@@ -571,6 +576,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	unsigned long flags, end_jiffies;
 	int retry;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, 0);
 
@@ -882,6 +890,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
@@ -911,3 +922,19 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	RREG32(mmVM_INVALIDATE_RESPONSE);
 	return 0;
 }
+
+ /**
+  * read_vmid_from_vmfault_reg - read vmid from register
+  *
+  * adev: amdgpu_device pointer
+  * @vmid: vmid pointer
+  * read vmid from register (CIK).
+  */
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
+
+	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c

@@ -176,6 +176,9 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
@@ -568,6 +571,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	int retry;
 	struct vi_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -844,6 +850,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -213,6 +213,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
@@ -679,6 +681,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -866,6 +871,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	if (ring->ready)
 		return invalidate_tlbs_with_kiq(adev, pasid);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -1621,6 +1621,20 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 	return ret;
 }
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *mem)
+{
+	struct amdgpu_device *adev;
+
+	adev = (struct amdgpu_device *)kgd;
+	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
+		*mem = *adev->gmc.vm_fault_info;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+	}
+	return 0;
+}
+
 /* Evict a userptr BO by stopping the queues if necessary
  *
  * Runs in MMU notifier, may be in RECLAIM_FS context. This means it

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3307,6 +3307,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
 
+	/* Block kfd */
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
@@ -3322,7 +3325,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		if (job && job->base.sched == &ring->sched)
 			continue;
 
-		drm_sched_hw_job_reset(&ring->sched, &job->base);
+		drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
@@ -3363,6 +3366,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
+	/*unlock kfd */
+	amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h

@@ -105,6 +105,8 @@ struct amdgpu_gmc {
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
 	bool			translate_further;
+	struct kfd_vm_fault_info *vm_fault_info;
+	atomic_t		vm_fault_info_updated;
 
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -495,11 +495,12 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 	eaddr = eaddr & ((1 << shift) - 1);
 
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	if (vm->root.base.bo->shadow)
+		flags |= AMDGPU_GEM_CREATE_SHADOW;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	else
-		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				AMDGPU_GEM_CREATE_SHADOW);
+		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = from; pt_idx <= to; ++pt_idx) {
@@ -2587,7 +2588,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	else
+	else if (vm_context != AMDGPU_VM_CONTEXT_COMPUTE)
 		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
@@ -2662,8 +2663,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * - pasid (old PASID is released, because compute manages its own PASIDs)
  *
  * Reinitializes the page directory to reflect the changed ATS
- * setting. May leave behind an unused shadow BO for the page
- * directory when switching from SDMA updates to CPU updates.
+ * setting.
  *
  * Returns:
  * 0 for success, -errno for errors.
@@ -2713,6 +2713,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	/* Free the shadow bo for compute VM */
+	amdgpu_bo_unref(&vm->root.base.bo->shadow);
+
 error:
 	amdgpu_bo_unreserve(vm->root.base.bo);
 	return r;

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -28,6 +28,7 @@
 #include "cik.h"
 #include "gmc_v7_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
@@ -1078,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1087,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v7_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1276,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
 	status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
@@ -1301,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c

@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
@@ -1182,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1191,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v8_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1426,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	if (amdgpu_sriov_vf(adev)) {
 		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
@@ -1463,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 

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

@@ -25,12 +25,39 @@
 #include "cik_int.h"
 
 static bool cik_event_interrupt_isr(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
+	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 	unsigned int vmid, pasid;
 
+	/* This workaround is due to HW/FW limitation on Hawaii that
+	 * VMID and PASID are not written into ih_ring_entry
+	 */
+	if ((ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) &&
+		dev->device_info->asic_family == CHIP_HAWAII) {
+		struct cik_ih_ring_entry *tmp_ihre =
+			(struct cik_ih_ring_entry *)patched_ihre;
+
+		*patched_flag = true;
+		*tmp_ihre = *ihre;
+
+		vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd);
+		pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid);
+
+		tmp_ihre->ring_id &= 0x000000ff;
+		tmp_ihre->ring_id |= vmid << 8;
+		tmp_ihre->ring_id |= pasid << 16;
+
+		return (pasid != 0) &&
+			vmid >= dev->vm_info.first_vmid_kfd &&
+			vmid <= dev->vm_info.last_vmid_kfd;
+	}
+
 	/* Only handle interrupts from KFD VMIDs */
 	vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
 	if (vmid < dev->vm_info.first_vmid_kfd ||
@@ -48,18 +75,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 	return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
 		ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
 		ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
-		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE;
+		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE ||
+		ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT;
 }
 
 static void cik_event_interrupt_wq(struct kfd_dev *dev,
 					const uint32_t *ih_ring_entry)
 {
-	unsigned int pasid;
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
-
-	pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
+	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
@@ -72,6 +100,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 		kfd_signal_event_interrupt(pasid, context_id & 0xff, 8);
 	else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE)
 		kfd_signal_hw_exception_event(pasid);
+	else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) {
+		struct kfd_vm_fault_info info;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+
+		memset(&info, 0, sizeof(info));
+		dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info);
+		if (!info.page_addr && !info.status)
+			return;
+
+		if (info.vmid == vmid)
+			kfd_signal_vm_fault_event(dev, pasid, &info);
+		else
+			kfd_signal_vm_fault_event(dev, pasid, NULL);
+	}
 }
 
 const struct kfd_event_interrupt_class event_interrupt_class_cik = {

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

@@ -20,8 +20,8 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#ifndef HSA_RADEON_CIK_INT_H_INCLUDED
-#define HSA_RADEON_CIK_INT_H_INCLUDED
+#ifndef CIK_INT_H_INCLUDED
+#define CIK_INT_H_INCLUDED
 
 #include <linux/types.h>
 
@@ -34,9 +34,10 @@ struct cik_ih_ring_entry {
 
 #define CIK_INTSRC_CP_END_OF_PIPE	0xB5
 #define CIK_INTSRC_CP_BAD_OPCODE	0xB7
-#define CIK_INTSRC_DEQUEUE_COMPLETE	0xC6
 #define CIK_INTSRC_SDMA_TRAP		0xE0
 #define CIK_INTSRC_SQ_INTERRUPT_MSG	0xEF
+#define CIK_INTSRC_GFX_PAGE_INV_FAULT	0x92
+#define CIK_INTSRC_GFX_MEM_PROT_FAULT	0x93
 
 #endif
 

drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm

@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
 var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE     = 9
@@ -251,7 +255,7 @@ if (!EMU_RUN_HACK)
     s_waitcnt lgkmcnt(0)
     s_or_b32        ttmp7, ttmp8, ttmp9
     s_cbranch_scc0  L_NO_NEXT_TRAP //next level trap handler not been set
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_setpc_b64     [ttmp8,ttmp9] //jump to next level trap handler
 
 L_NO_NEXT_TRAP:
@@ -262,7 +266,7 @@ L_NO_NEXT_TRAP:
     s_addc_u32  ttmp1, ttmp1, 0
 L_EXCP_CASE:
     s_and_b32   ttmp1, ttmp1, 0xFFFF
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_rfe_b64       [ttmp0, ttmp1]
 end
     // *********        End handling of non-CWSR traps   *******************
@@ -1053,7 +1057,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
     s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier                                                   //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1134,3 +1138,11 @@ end
 function get_hwreg_size_bytes
     return 128 //HWREG size 128 bytes
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end

drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm

@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK       = 0x2000
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT	= 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE	= 9
@@ -317,7 +321,7 @@ L_EXCP_CASE:
     // Restore SQ_WAVE_STATUS.
     s_and_b64       exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64       vcc, vcc, vcc    // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status
+    set_status_without_spi_prio(s_save_status, ttmp2)
 
     s_rfe_b64       [ttmp0, ttmp1]
 end
@@ -1120,7 +1124,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff	//pc[47:32]	   //Do it here in order not to affect STATUS
     s_and_b64	 exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64	 vcc, vcc, vcc	// Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status	 // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier							//barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1212,3 +1216,11 @@ function ack_sqc_store_workaround
         s_waitcnt lgkmcnt(0)
     end
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end

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

@@ -122,6 +122,9 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
+	if (kfd_is_locked())
+		return -EAGAIN;
+
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
 
@@ -389,6 +392,61 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 	return retval;
 }
 
+static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p,
+					void *data)
+{
+	int retval;
+	const int max_num_cus = 1024;
+	struct kfd_ioctl_set_cu_mask_args *args = data;
+	struct queue_properties properties;
+	uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr;
+	size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32);
+
+	if ((args->num_cu_mask % 32) != 0) {
+		pr_debug("num_cu_mask 0x%x must be a multiple of 32",
+				args->num_cu_mask);
+		return -EINVAL;
+	}
+
+	properties.cu_mask_count = args->num_cu_mask;
+	if (properties.cu_mask_count == 0) {
+		pr_debug("CU mask cannot be 0");
+		return -EINVAL;
+	}
+
+	/* To prevent an unreasonably large CU mask size, set an arbitrary
+	 * limit of max_num_cus bits.  We can then just drop any CU mask bits
+	 * past max_num_cus bits and just use the first max_num_cus bits.
+	 */
+	if (properties.cu_mask_count > max_num_cus) {
+		pr_debug("CU mask cannot be greater than 1024 bits");
+		properties.cu_mask_count = max_num_cus;
+		cu_mask_size = sizeof(uint32_t) * (max_num_cus/32);
+	}
+
+	properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL);
+	if (!properties.cu_mask)
+		return -ENOMEM;
+
+	retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size);
+	if (retval) {
+		pr_debug("Could not copy CU mask from userspace");
+		kfree(properties.cu_mask);
+		return -EFAULT;
+	}
+
+	mutex_lock(&p->mutex);
+
+	retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties);
+
+	mutex_unlock(&p->mutex);
+
+	if (retval)
+		kfree(properties.cu_mask);
+
+	return retval;
+}
+
 static int kfd_ioctl_set_memory_policy(struct file *filep,
 					struct kfd_process *p, void *data)
 {
@@ -754,7 +812,6 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 {
 	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
-	struct timespec64 time;
 
 	dev = kfd_device_by_id(args->gpu_id);
 	if (dev)
@@ -766,11 +823,8 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 		args->gpu_clock_counter = 0;
 
 	/* No access to rdtsc. Using raw monotonic time */
-	getrawmonotonic64(&time);
-	args->cpu_clock_counter = (uint64_t)timespec64_to_ns(&time);
-
-	get_monotonic_boottime64(&time);
-	args->system_clock_counter = (uint64_t)timespec64_to_ns(&time);
+	args->cpu_clock_counter = ktime_get_raw_ns();
+	args->system_clock_counter = ktime_get_boot_ns();
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
 	args->system_clock_freq = 1000000000;
@@ -1558,6 +1612,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU,
 			kfd_ioctl_unmap_memory_from_gpu, 0),
 
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_CU_MASK,
+			kfd_ioctl_set_cu_mask, 0),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)

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

@@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu,
 	return 0;
 }
 
+static struct kfd_mem_properties *
+find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width,
+		struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *props;
+
+	list_for_each_entry(props, &dev->mem_props, list) {
+		if (props->heap_type == heap_type
+				&& props->flags == flags
+				&& props->width == width)
+			return props;
+	}
+
+	return NULL;
+}
 /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
  * topology device present in the device_list
  */
@@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem,
 {
 	struct kfd_mem_properties *props;
 	struct kfd_topology_device *dev;
+	uint32_t heap_type;
+	uint64_t size_in_bytes;
+	uint32_t flags = 0;
+	uint32_t width;
 
 	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
 			mem->proximity_domain);
 	list_for_each_entry(dev, device_list, list) {
 		if (mem->proximity_domain == dev->proximity_domain) {
-			props = kfd_alloc_struct(props);
-			if (!props)
-				return -ENOMEM;
-
 			/* We're on GPU node */
 			if (dev->node_props.cpu_cores_count == 0) {
 				/* APU */
 				if (mem->visibility_type == 0)
-					props->heap_type =
+					heap_type =
 						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
 				/* dGPU */
 				else
-					props->heap_type = mem->visibility_type;
+					heap_type = mem->visibility_type;
 			} else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+				heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
 
 			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+				flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
 			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+				flags |= HSA_MEM_FLAGS_NON_VOLATILE;
 
-			props->size_in_bytes =
+			size_in_bytes =
 				((uint64_t)mem->length_high << 32) +
 							mem->length_low;
-			props->width = mem->width;
+			width = mem->width;
+
+			/* Multiple banks of the same type are aggregated into
+			 * one. User mode doesn't care about multiple physical
+			 * memory segments. It's managed as a single virtual
+			 * heap for user mode.
+			 */
+			props = find_subtype_mem(heap_type, flags, width, dev);
+			if (props) {
+				props->size_in_bytes += size_in_bytes;
+				break;
+			}
+
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->heap_type = heap_type;
+			props->flags = flags;
+			props->size_in_bytes = size_in_bytes;
+			props->width = width;
 
 			dev->node_props.mem_banks_count++;
 			list_add_tail(&props->list, &dev->mem_props);

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

@@ -38,7 +38,6 @@
 #include "kfd_dbgmgr.h"
 #include "kfd_dbgdev.h"
 #include "kfd_device_queue_manager.h"
-#include "../../radeon/cik_reg.h"
 
 static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 {

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

@@ -60,6 +60,9 @@ enum {
 	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,
@@ -190,4 +193,38 @@ union ULARGE_INTEGER {
 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_ */

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

@@ -21,6 +21,8 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
 #include "kfd_priv.h"
 
 static struct dentry *debugfs_root;
@@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, show, NULL);
 }
 
+static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
+	const char __user *user_buf, size_t size, loff_t *ppos)
+{
+	struct kfd_dev *dev;
+	char tmp[16];
+	uint32_t gpu_id;
+	int ret = -EINVAL;
+
+	memset(tmp, 0, 16);
+	if (size >= 16) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	if (copy_from_user(tmp, user_buf, size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (kstrtoint(tmp, 10, &gpu_id)) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	dev = kfd_device_by_id(gpu_id);
+	if (dev) {
+		kfd_debugfs_hang_hws(dev);
+		ret = size;
+	} else
+		pr_err("Cannot find device %d.\n", gpu_id);
+
+out:
+	return ret;
+}
+
 static const struct file_operations kfd_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = kfd_debugfs_open,
@@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = {
 	.release = single_release,
 };
 
+static const struct file_operations kfd_debugfs_hang_hws_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.write = kfd_debugfs_hang_hws_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void kfd_debugfs_init(void)
 {
 	struct dentry *ent;
@@ -65,6 +108,11 @@ void kfd_debugfs_init(void)
 	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
+
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+				  NULL,
+				  &kfd_debugfs_hang_hws_fops);
+
 	if (!ent)
 		pr_warn("Failed to create rls in kfd debugfs\n");
 }

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

@@ -30,7 +30,13 @@
 #include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
-static atomic_t kfd_device_suspended = ATOMIC_INIT(0);
+
+/*
+ * kfd_locked is used to lock the kfd driver during suspend or reset
+ * once locked, kfd driver will stop any further GPU execution.
+ * create process (open) will return -EAGAIN.
+ */
+static atomic_t kfd_locked = ATOMIC_INIT(0);
 
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
@@ -46,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -61,6 +68,22 @@ static const struct kfd_device_info carrizo_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
+};
+
+static const struct kfd_device_info raven_device_info = {
+	.asic_family = CHIP_RAVEN,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = true,
+	.num_sdma_engines = 1,
 };
 #endif
 
@@ -77,6 +100,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_device_info = {
@@ -91,6 +115,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_vf_device_info = {
@@ -105,6 +130,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_device_info = {
@@ -119,6 +145,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_vf_device_info = {
@@ -133,6 +160,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -148,6 +176,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris10_vf_device_info = {
@@ -162,6 +191,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris11_device_info = {
@@ -176,6 +206,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_device_info = {
@@ -190,6 +221,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_vf_device_info = {
@@ -204,6 +236,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -241,6 +274,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9875, &carrizo_device_info },	/* Carrizo */
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
+	{ 0x15DD, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
@@ -514,13 +548,54 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 	kfree(kfd);
 }
 
+int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+{
+	if (!kfd->init_complete)
+		return 0;
+	kgd2kfd_suspend(kfd);
+
+	/* hold dqm->lock to prevent further execution*/
+	dqm_lock(kfd->dqm);
+
+	kfd_signal_reset_event(kfd);
+	return 0;
+}
+
+/*
+ * Fix me. KFD won't be able to resume existing process for now.
+ * We will keep all existing process in a evicted state and
+ * wait the process to be terminated.
+ */
+
+int kgd2kfd_post_reset(struct kfd_dev *kfd)
+{
+	int ret, count;
+
+	if (!kfd->init_complete)
+		return 0;
+
+	dqm_unlock(kfd->dqm);
+
+	ret = kfd_resume(kfd);
+	if (ret)
+		return ret;
+	count = atomic_dec_return(&kfd_locked);
+	WARN_ONCE(count != 0, "KFD reset ref. error");
+	return 0;
+}
+
+bool kfd_is_locked(void)
+{
+	return  (atomic_read(&kfd_locked) > 0);
+}
+
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return;
 
 	/* For first KFD device suspend all the KFD processes */
-	if (atomic_inc_return(&kfd_device_suspended) == 1)
+	if (atomic_inc_return(&kfd_locked) == 1)
 		kfd_suspend_all_processes();
 
 	kfd->dqm->ops.stop(kfd->dqm);
@@ -539,7 +614,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd)
 	if (ret)
 		return ret;
 
-	count = atomic_dec_return(&kfd_device_suspended);
+	count = atomic_dec_return(&kfd_locked);
 	WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
 	if (count == 0)
 		ret = kfd_resume_all_processes();
@@ -577,14 +652,24 @@ static int kfd_resume(struct kfd_dev *kfd)
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
+	uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
+	bool is_patched = false;
+
 	if (!kfd->init_complete)
 		return;
 
+	if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) {
+		dev_err_once(kfd_device, "Ring entry too small\n");
+		return;
+	}
+
 	spin_lock(&kfd->interrupt_lock);
 
 	if (kfd->interrupts_active
-	    && interrupt_is_wanted(kfd, ih_ring_entry)
-	    && enqueue_ih_ring_entry(kfd, ih_ring_entry))
+	    && interrupt_is_wanted(kfd, ih_ring_entry,
+				   patched_ihre, &is_patched)
+	    && enqueue_ih_ring_entry(kfd,
+				     is_patched ? patched_ihre : ih_ring_entry))
 		queue_work(kfd->ih_wq, &kfd->interrupt_work);
 
 	spin_unlock(&kfd->interrupt_lock);
@@ -739,8 +824,8 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
 	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
 		return -ENOMEM;
 
-	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
-	if ((*mem_obj) == NULL)
+	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
+	if (!(*mem_obj))
 		return -ENOMEM;
 
 	pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size);
@@ -857,3 +942,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
 	kfree(mem_obj);
 	return 0;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+/* This function will send a package to HIQ to hang the HWS
+ * which will trigger a GPU reset and bring the HWS back to normal state
+ */
+int kfd_debugfs_hang_hws(struct kfd_dev *dev)
+{
+	int r = 0;
+
+	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
+		pr_err("HWS is not enabled");
+		return -EINVAL;
+	}
+
+	r = pm_debugfs_hang_hws(&dev->dqm->packets);
+	if (!r)
+		r = dqm_debugfs_execute_queues(dev->dqm);
+
+	return r;
+}
+
+#endif

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

@@ -26,15 +26,14 @@
 
 #include <linux/rwsem.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
 #define KFD_UNMAP_LATENCY_MS			(4000)
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
-
-#define CIK_SDMA_QUEUES				(4)
-#define CIK_SDMA_QUEUES_PER_ENGINE		(2)
-#define CIK_SDMA_ENGINE_NUM			(2)
+#define KFD_SDMA_QUEUES_PER_ENGINE		(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;
@@ -170,11 +169,12 @@ struct device_queue_manager {
 	struct device_queue_manager_ops ops;
 	struct device_queue_manager_asic_ops asic_ops;
 
-	struct mqd_manager	*mqds[KFD_MQD_TYPE_MAX];
+	struct mqd_manager	*mqd_mgrs[KFD_MQD_TYPE_MAX];
 	struct packet_manager	packets;
 	struct kfd_dev		*dev;
-	struct mutex		lock;
+	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
 	struct list_head	queues;
+	unsigned int		saved_flags;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
 	unsigned int		sdma_queue_count;
@@ -190,6 +190,10 @@ struct device_queue_manager {
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;
+
+	/* hw exception  */
+	bool			is_hws_hang;
+	struct work_struct	hw_exception_work;
 };
 
 void device_queue_manager_init_cik(
@@ -207,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
@@ -219,4 +224,19 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 	return (pdd->lds_base >> 60) & 0x0E;
 }
 
+/* The DQM lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void dqm_lock(struct device_queue_manager *dqm)
+{
+	mutex_lock(&dqm->lock_hidden);
+	dqm->saved_flags = memalloc_nofs_save();
+}
+static inline void dqm_unlock(struct device_queue_manager *dqm)
+{
+	memalloc_nofs_restore(dqm->saved_flags);
+	mutex_unlock(&dqm->lock_hidden);
+}
+
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c

@@ -60,7 +60,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (vega10_noretry &&
+		if (noretry &&
 		    !dqm->dev->device_info->needs_iommu_device)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;

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

@@ -188,9 +188,9 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	*doorbell_off = kfd->doorbell_id_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
-			 "     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == %p\n",
-		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
+			"     doorbell offset   == 0x%08X\n"
+			"     doorbell index    == 0x%x\n",
+		*doorbell_off, inx);
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 {
 	unsigned int inx;
 
-	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr)
+		* sizeof(u32) / kfd->device_info->doorbell_size;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_available_index);

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

@@ -850,6 +850,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 				ev->memory_exception_data = *ev_data;
 		}
 
+	if (type == KFD_EVENT_TYPE_MEMORY) {
+		dev_warn(kfd_device,
+			"Sending SIGSEGV to HSA Process with PID %d ",
+				p->lead_thread->pid);
+		send_sig(SIGSEGV, p->lead_thread, 0);
+	}
+
 	/* Send SIGTERM no event of type "type" has been found*/
 	if (send_signal) {
 		if (send_sigterm) {
@@ -904,34 +911,41 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	memory_exception_data.failure.NotPresent = 1;
 	memory_exception_data.failure.NoExecute = 0;
 	memory_exception_data.failure.ReadOnly = 0;
-	if (vma) {
-		if (vma->vm_start > address) {
-			memory_exception_data.failure.NotPresent = 1;
-			memory_exception_data.failure.NoExecute = 0;
+	if (vma && address >= vma->vm_start) {
+		memory_exception_data.failure.NotPresent = 0;
+
+		if (is_write_requested && !(vma->vm_flags & VM_WRITE))
+			memory_exception_data.failure.ReadOnly = 1;
+		else
 			memory_exception_data.failure.ReadOnly = 0;
-		} else {
-			memory_exception_data.failure.NotPresent = 0;
-			if (is_write_requested && !(vma->vm_flags & VM_WRITE))
-				memory_exception_data.failure.ReadOnly = 1;
-			else
-				memory_exception_data.failure.ReadOnly = 0;
-			if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
-				memory_exception_data.failure.NoExecute = 1;
-			else
-				memory_exception_data.failure.NoExecute = 0;
-		}
+
+		if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
+			memory_exception_data.failure.NoExecute = 1;
+		else
+			memory_exception_data.failure.NoExecute = 0;
 	}
 
 	up_read(&mm->mmap_sem);
 	mmput(mm);
 
-	mutex_lock(&p->event_mutex);
+	pr_debug("notpresent %d, noexecute %d, readonly %d\n",
+			memory_exception_data.failure.NotPresent,
+			memory_exception_data.failure.NoExecute,
+			memory_exception_data.failure.ReadOnly);
 
-	/* Lookup events by type and signal them */
-	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
-			&memory_exception_data);
+	/* Workaround on Raven to not kill the process when memory is freed
+	 * before IOMMU is able to finish processing all the excessive PPRs
+	 */
+	if (dev->device_info->asic_family != CHIP_RAVEN) {
+		mutex_lock(&p->event_mutex);
+
+		/* Lookup events by type and signal them */
+		lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
+				&memory_exception_data);
+
+		mutex_unlock(&p->event_mutex);
+	}
 
-	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
@@ -956,3 +970,67 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
+
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info)
+{
+	struct kfd_event *ev;
+	uint32_t id;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct kfd_hsa_memory_exception_data memory_exception_data;
+
+	if (!p)
+		return; /* Presumably process exited. */
+	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.failure.imprecise = 1;
+	/* Set failure reason */
+	if (info) {
+		memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
+		memory_exception_data.failure.NotPresent =
+			info->prot_valid ? 1 : 0;
+		memory_exception_data.failure.NoExecute =
+			info->prot_exec ? 1 : 0;
+		memory_exception_data.failure.ReadOnly =
+			info->prot_write ? 1 : 0;
+		memory_exception_data.failure.imprecise = 0;
+	}
+	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_MEMORY) {
+			ev->memory_exception_data = memory_exception_data;
+			set_event(ev);
+		}
+
+	mutex_unlock(&p->event_mutex);
+	kfd_unref_process(p);
+}
+
+void kfd_signal_reset_event(struct kfd_dev *dev)
+{
+	struct kfd_hsa_hw_exception_data hw_exception_data;
+	struct kfd_process *p;
+	struct kfd_event *ev;
+	unsigned int temp;
+	uint32_t id, idx;
+
+	/* 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;
+
+	idx = srcu_read_lock(&kfd_processes_srcu);
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		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;
+				set_event(ev);
+			}
+		mutex_unlock(&p->event_mutex);
+	}
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+}

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

@@ -66,6 +66,7 @@ struct kfd_event {
 	/* type specific data */
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};
 };
 

drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c

@@ -26,7 +26,9 @@
 
 
 static bool event_interrupt_isr_v9(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	uint16_t source_id, client_id, pasid, vmid;
 	const uint32_t *data = ih_ring_entry;
@@ -57,7 +59,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev,
 	return source_id == SOC15_INTSRC_CP_END_OF_PIPE ||
 		source_id == SOC15_INTSRC_SDMA_TRAP ||
 		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
-		source_id == SOC15_INTSRC_CP_BAD_OPCODE;
+		source_id == SOC15_INTSRC_CP_BAD_OPCODE ||
+		client_id == SOC15_IH_CLIENTID_VMC ||
+		client_id == SOC15_IH_CLIENTID_UTCL2;
 }
 
 static void event_interrupt_wq_v9(struct kfd_dev *dev,
@@ -82,7 +86,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 		kfd_signal_hw_exception_event(pasid);
 	else if (client_id == SOC15_IH_CLIENTID_VMC ||
 		 client_id == SOC15_IH_CLIENTID_UTCL2) {
-		/* TODO */
+		struct kfd_vm_fault_info info = {0};
+		uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
+
+		info.vmid = vmid;
+		info.mc_id = client_id;
+		info.page_addr = ih_ring_entry[4] |
+			(uint64_t)(ih_ring_entry[5] & 0xf) << 32;
+		info.prot_valid = ring_id & 0x08;
+		info.prot_read  = ring_id & 0x10;
+		info.prot_write = ring_id & 0x20;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_signal_vm_fault_event(dev, pasid, &info);
 	}
 }
 

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

@@ -151,13 +151,15 @@ static void interrupt_wq(struct work_struct *work)
 								ih_ring_entry);
 }
 
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry)
+bool interrupt_is_wanted(struct kfd_dev *dev,
+			const uint32_t *ih_ring_entry,
+			uint32_t *patched_ihre, bool *flag)
 {
 	/* integer and bitwise OR so there is no boolean short-circuiting */
 	unsigned int wanted = 0;
 
 	wanted |= dev->device_info->event_interrupt_class->interrupt_isr(dev,
-								ih_ring_entry);
+					 ih_ring_entry, patched_ihre, flag);
 
 	return wanted != 0;
 }

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

@@ -190,7 +190,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 {
 	struct kfd_dev *dev;
 
-	dev_warn(kfd_device,
+	dev_warn_ratelimited(kfd_device,
 			"Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X",
 			PCI_BUS_NUM(pdev->devfn),
 			PCI_SLOT(pdev->devfn),

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

@@ -59,7 +59,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	switch (type) {
 	case KFD_QUEUE_TYPE_DIQ:
 	case KFD_QUEUE_TYPE_HIQ:
-		kq->mqd = dev->dqm->ops.get_mqd_manager(dev->dqm,
+		kq->mqd_mgr = dev->dqm->ops.get_mqd_manager(dev->dqm,
 						KFD_MQD_TYPE_HIQ);
 		break;
 	default:
@@ -67,7 +67,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		return false;
 	}
 
-	if (!kq->mqd)
+	if (!kq->mqd_mgr)
 		return false;
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
@@ -123,6 +123,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr;
 	prop.eop_ring_buffer_address = kq->eop_gpu_addr;
 	prop.eop_ring_buffer_size = PAGE_SIZE;
+	prop.cu_mask = NULL;
 
 	if (init_queue(&kq->queue, &prop) != 0)
 		goto err_init_queue;
@@ -130,7 +131,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->queue->device = dev;
 	kq->queue->process = kfd_get_process(current);
 
-	retval = kq->mqd->init_mqd(kq->mqd, &kq->queue->mqd,
+	retval = kq->mqd_mgr->init_mqd(kq->mqd_mgr, &kq->queue->mqd,
 					&kq->queue->mqd_mem_obj,
 					&kq->queue->gart_mqd_addr,
 					&kq->queue->properties);
@@ -142,9 +143,9 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		pr_debug("Assigning hiq to hqd\n");
 		kq->queue->pipe = KFD_CIK_HIQ_PIPE;
 		kq->queue->queue = KFD_CIK_HIQ_QUEUE;
-		kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe,
-				  kq->queue->queue, &kq->queue->properties,
-				  NULL);
+		kq->mqd_mgr->load_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->pipe, kq->queue->queue,
+				&kq->queue->properties, NULL);
 	} else {
 		/* allocate fence for DIQ */
 
@@ -182,7 +183,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 static void uninitialize(struct kernel_queue *kq)
 {
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
-		kq->mqd->destroy_mqd(kq->mqd,
+		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					KFD_UNMAP_LATENCY_MS,
@@ -191,7 +192,8 @@ static void uninitialize(struct kernel_queue *kq)
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
-	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+	kq->mqd_mgr->uninit_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->mqd_mem_obj);
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);

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

@@ -70,7 +70,7 @@ struct kernel_queue {
 
 	/* data */
 	struct kfd_dev		*dev;
-	struct mqd_manager	*mqd;
+	struct mqd_manager	*mqd_mgr;
 	struct queue		*queue;
 	uint64_t		pending_wptr64;
 	uint32_t		pending_wptr;

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

@@ -47,6 +47,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
+	.pre_reset	= kgd2kfd_pre_reset,
+	.post_reset	= kgd2kfd_post_reset,
 };
 
 int sched_policy = KFD_SCHED_POLICY_HWS;
@@ -61,7 +63,7 @@ MODULE_PARM_DESC(hws_max_conc_proc,
 
 int cwsr_enable = 1;
 module_param(cwsr_enable, int, 0444);
-MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))");
+MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = off, 1 = on (default))");
 
 int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
 module_param(max_num_of_queues_per_device, int, 0444);
@@ -83,13 +85,19 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
-int vega10_noretry;
-module_param_named(noretry, vega10_noretry, int, 0644);
+int noretry;
+module_param(noretry, int, 0644);
 MODULE_PARM_DESC(noretry,
-	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
+	"Set sh_mem_config.retry_disable on GFXv9+ dGPUs (0 = retry enabled (default), 1 = retry disabled)");
+
+int halt_if_hws_hang;
+module_param(halt_if_hws_hang, int, 0644);
+MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
 
 static int amdkfd_init_completed;
 
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {

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

@@ -21,7 +21,7 @@
  *
  */
 
-#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
 
 struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 					struct kfd_dev *dev)
@@ -48,3 +48,42 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 
 	return NULL;
 }
+
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask)
+{
+	struct kfd_cu_info cu_info;
+	uint32_t cu_per_sh[4] = {0};
+	int i, se, cu = 0;
+
+	mm->dev->kfd2kgd->get_cu_info(mm->dev->kgd, &cu_info);
+
+	if (cu_mask_count > cu_info.cu_active_number)
+		cu_mask_count = cu_info.cu_active_number;
+
+	for (se = 0; se < cu_info.num_shader_engines; se++)
+		for (i = 0; i < 4; i++)
+			cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]);
+
+	/* Symmetrically map cu_mask to all SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0;
+	 * cu_mask[0] bit1 -> se_mask[1] bit0;
+	 * ... (if # SE is 4)
+	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+	 * ...
+	 */
+	se = 0;
+	for (i = 0; i < cu_mask_count; i++) {
+		if (cu_mask[i / 32] & (1 << (i % 32)))
+			se_mask[se] |= 1 << cu;
+
+		do {
+			se++;
+			if (se == cu_info.num_shader_engines) {
+				se = 0;
+				cu++;
+			}
+		} while (cu >= cu_per_sh[se] && cu < 32);
+	}
+}

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

@@ -93,4 +93,8 @@ struct mqd_manager {
 	struct kfd_dev	*dev;
 };
 
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask);
+
 #endif /* KFD_MQD_MANAGER_H_ */

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

@@ -41,6 +41,31 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
 	return (struct cik_sdma_rlc_registers *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct cik_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -408,7 +435,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 

drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c

@@ -41,6 +41,31 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct v9_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -55,7 +80,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	 * instead of sub-allocation function.
 	 */
 	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
-		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
 		if (!*mqd_mem_obj)
 			return -ENOMEM;
 		retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd,
@@ -198,6 +223,8 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -393,7 +420,7 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 

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

@@ -43,6 +43,31 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct vi_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct vi_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 			atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT |
 			mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -394,7 +421,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 

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

@@ -418,4 +418,30 @@ int pm_debugfs_runlist(struct seq_file *m, void *data)
 	return 0;
 }
 
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+
+	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
+		buffer[0], buffer[1], buffer[2], buffer[3],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
 #endif

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

@@ -73,7 +73,7 @@
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
- * the radeon driver to a fixed hqd slot, here are the fixed HIQ hqd slot
+ * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
  * definitions for Kaveri. In Kaveri only the first ME queues participates
  * in the cp scheduling taking that in mind we set the HIQ slot in the
  * second ME.
@@ -142,7 +142,12 @@ extern int ignore_crat;
 /*
  * Set sh_mem_config.retry_disable on Vega10
  */
-extern int vega10_noretry;
+extern int noretry;
+
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
 
 /**
  * enum kfd_sched_policy
@@ -180,9 +185,10 @@ enum cache_policy {
 
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry, uint32_t *patched_ihre,
+			bool *patched_flag);
 	void (*interrupt_wq)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry);
 };
 
 struct kfd_device_info {
@@ -197,6 +203,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	unsigned int num_sdma_engines;
 };
 
 struct kfd_mem_obj {
@@ -415,6 +422,9 @@ struct queue_properties {
 	uint32_t ctl_stack_size;
 	uint64_t tba_addr;
 	uint64_t tma_addr;
+	/* Relevant for CU */
+	uint32_t cu_mask_count; /* Must be a multiple of 32 */
+	uint32_t *cu_mask;
 };
 
 /**
@@ -806,12 +816,18 @@ int kfd_interrupt_init(struct kfd_dev *dev);
 void kfd_interrupt_exit(struct kfd_dev *dev);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry);
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry);
+bool interrupt_is_wanted(struct kfd_dev *dev,
+				const uint32_t *ih_ring_entry,
+				uint32_t *patched_ihre, bool *flag);
 
 /* Power Management */
 void kgd2kfd_suspend(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd);
 
+/* GPU reset */
+int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_post_reset(struct kfd_dev *kfd);
+
 /* amdkfd Apertures */
 int kfd_init_apertures(struct kfd_process *process);
 
@@ -838,6 +854,7 @@ 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);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -858,6 +875,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p);
 struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
 						unsigned int qid);
 
@@ -964,10 +983,17 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info);
+
+void kfd_signal_reset_event(struct kfd_dev *dev);
+
 void kfd_flush_tlb(struct kfd_process_device *pdd);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
+bool kfd_is_locked(void);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
@@ -980,6 +1006,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data);
 int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
 int pm_debugfs_runlist(struct seq_file *m, void *data);
 
+int kfd_debugfs_hang_hws(struct kfd_dev *dev);
+int pm_debugfs_hang_hws(struct packet_manager *pm);
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+
 #else
 
 static inline void kfd_debugfs_init(void) {}

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

@@ -244,6 +244,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 		return ERR_PTR(-EINVAL);
 
 	process = find_process(thread);
+	if (!process)
+		return ERR_PTR(-EINVAL);
 
 	return process;
 }

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

@@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >=
-			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
 			pr_err("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;
@@ -209,7 +208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		     KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
 		((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) ||
 		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
-			pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
+			pr_debug("Over-subscription is not allowed when amdkfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
@@ -326,6 +325,8 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			if (retval != -ETIME)
 				goto err_destroy_queue;
 		}
+		kfree(pqn->q->properties.cu_mask);
+		pqn->q->properties.cu_mask = NULL;
 		uninit_queue(pqn->q);
 	}
 
@@ -366,6 +367,34 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	return 0;
 }
 
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p)
+{
+	int retval;
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("No queue %d exists for update operation\n", qid);
+		return -EFAULT;
+	}
+
+	/* Free the old CU mask memory if it is already allocated, then
+	 * allocate memory for the new CU mask.
+	 */
+	kfree(pqn->q->properties.cu_mask);
+
+	pqn->q->properties.cu_mask_count = p->cu_mask_count;
+	pqn->q->properties.cu_mask = p->cu_mask;
+
+	retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
+							pqn->q);
+	if (retval != 0)
+		return retval;
+
+	return 0;
+}
+
 struct kernel_queue *pqm_get_kernel_queue(
 					struct process_queue_manager *pqm,
 					unsigned int qid)
@@ -387,7 +416,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 	struct process_queue_node *pqn;
 	struct queue *q;
 	enum KFD_MQD_TYPE mqd_type;
-	struct mqd_manager *mqd_manager;
+	struct mqd_manager *mqd_mgr;
 	int r = 0;
 
 	list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
@@ -410,11 +439,11 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 					   q->properties.type, q->device->id);
 				continue;
 			}
-			mqd_manager = q->device->dqm->ops.get_mqd_manager(
+			mqd_mgr = q->device->dqm->ops.get_mqd_manager(
 				q->device->dqm, mqd_type);
 		} else if (pqn->kq) {
 			q = pqn->kq->queue;
-			mqd_manager = pqn->kq->mqd;
+			mqd_mgr = pqn->kq->mqd_mgr;
 			switch (q->properties.type) {
 			case KFD_QUEUE_TYPE_DIQ:
 				seq_printf(m, "  DIQ on device %x\n",
@@ -434,7 +463,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 			continue;
 		}
 
-		r = mqd_manager->debugfs_show_mqd(m, q->mqd);
+		r = mqd_mgr->debugfs_show_mqd(m, q->mqd);
 		if (r != 0)
 			break;
 	}

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

@@ -47,6 +47,17 @@ enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 };
 
+struct kfd_vm_fault_info {
+	uint64_t	page_addr;
+	uint32_t	vmid;
+	uint32_t	mc_id;
+	uint32_t	status;
+	bool		prot_valid;
+	bool		prot_read;
+	bool		prot_write;
+	bool		prot_exec;
+};
+
 struct kfd_cu_info {
 	uint32_t num_shader_engines;
 	uint32_t num_shader_arrays_per_engine;
@@ -259,6 +270,21 @@ struct tile_config {
  * IB to the corresponding ring (ring type). The IB is executed with the
  * specified VMID in a user mode context.
  *
+ * @get_vm_fault_info: Return information about a recent VM fault on
+ * GFXv7 and v8. If multiple VM faults occurred since the last call of
+ * this function, it will return information about the first of those
+ * faults. On GFXv9 VM fault information is fully contained in the IH
+ * packet and this function is not needed.
+ *
+ * @read_vmid_from_vmfault_reg: On Hawaii the VMID is not set in the
+ * IH ring entry. This function allows the KFD ISR to get the VMID
+ * from the fault status register as early as possible.
+ *
+ * @gpu_recover: let kgd reset gpu after kfd detect CPC hang
+ *
+ * @set_compute_idle: Indicates that compute is idle on a device. This
+ * can be used to change power profiles depending on compute activity.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -374,6 +400,14 @@ struct kfd2kgd_calls {
 	int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine,
 			uint32_t vmid, uint64_t gpu_addr,
 			uint32_t *ib_cmd, uint32_t ib_len);
+
+	int (*get_vm_fault_info)(struct kgd_dev *kgd,
+			struct kfd_vm_fault_info *info);
+	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
+
+	void (*gpu_recover)(struct kgd_dev *kgd);
+
+	void (*set_compute_idle)(struct kgd_dev *kgd, bool idle);
 };
 
 /**
@@ -399,6 +433,10 @@ struct kfd2kgd_calls {
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
+ * @pre_reset: Notifies amdkfd that amdgpu about to reset the gpu
+ *
+ * @post_reset: Notify amdkfd that amgpu successfully reseted the gpu
+ *
  * This structure contains function callback pointers so the kgd driver
  * will notify to the amdkfd about certain status changes.
  *
@@ -417,6 +455,8 @@ struct kgd2kfd_calls {
 	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
+	int  (*pre_reset)(struct kfd_dev *kfd);
+	int  (*post_reset)(struct kfd_dev *kfd);
 };
 
 int kgd2kfd_init(unsigned interface_version,

include/uapi/linux/kfd_ioctl.h

@@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args {
 	__u32 queue_priority;	/* to KFD */
 };
 
+struct kfd_ioctl_set_cu_mask_args {
+	__u32 queue_id;		/* to KFD */
+	__u32 num_cu_mask;		/* to KFD */
+	__u64 cu_mask_ptr;		/* to KFD */
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -189,6 +195,15 @@ struct kfd_ioctl_dbg_wave_control_args {
 
 #define KFD_SIGNAL_EVENT_LIMIT			4096
 
+/* For kfd_event_data.hw_exception_data.reset_type. */
+#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET	0
+#define KFD_HW_EXCEPTION_PER_ENGINE_RESET	1
+
+/* For kfd_event_data.hw_exception_data.reset_cause. */
+#define KFD_HW_EXCEPTION_GPU_HANG	0
+#define KFD_HW_EXCEPTION_ECC		1
+
+
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */
 	__u32 event_trigger_data;	/* from KFD - signal events only */
@@ -219,7 +234,7 @@ struct kfd_memory_exception_failure {
 	__u32 NotPresent;	/* Page not present or supervisor privilege */
 	__u32 ReadOnly;	/* Write access to a read-only page */
 	__u32 NoExecute;	/* Execute access to a page marked NX */
-	__u32 pad;
+	__u32 imprecise;	/* Can't determine the	exact fault address */
 };
 
 /* memory exception data*/
@@ -230,10 +245,19 @@ struct kfd_hsa_memory_exception_data {
 	__u32 pad;
 };
 
-/* Event data*/
+/* hw exception data */
+struct kfd_hsa_hw_exception_data {
+	uint32_t reset_type;
+	uint32_t reset_cause;
+	uint32_t memory_lost;
+	uint32_t gpu_id;
+};
+
+/* Event data */
 struct kfd_event_data {
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};				/* From KFD */
 	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
@@ -448,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
 		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
 
+#define AMDKFD_IOC_SET_CU_MASK		\
+		AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1A
+#define AMDKFD_COMMAND_END		0x1B
 
 #endif