Merge branch 'drm-next-4.7' of git://people.freedesktop.org/~agd5f/linux into drm-next

More amdgpu fixes for 4.7.  Highlights:
- enable async pageflips
- UVD fixes for polaris
- lots of GPUVM fixes
- whitespace and code cleanups
- misc bug fixes

* 'drm-next-4.7' of git://people.freedesktop.org/~agd5f/linux: (32 commits)
  drm/amd/powerplay: rewrite pp_sw_init to make code readable
  drm/amdgpu/dce11: fix audio offset for asics with >7 audio pins
  drm/amdgpu: fix and cleanup user fence handling v2
  drm/amdgpu: move VM fields into job
  drm/amdgpu: move the context from the IBs into the job
  drm/amdgpu: move context switch handling into common code v2
  drm/amdgpu: move preamble IB handling into common code
  drm/amdgpu/gfx7: fix pipeline sync
  amdgpu/uvd: separate context buffer from DPB
  drm/amdgpu: use fence_context to judge ctx switch v2
  drm/amd/amdgpu:  Added more named DRM info messages for debugging
  drm/amd/amdgpu: Add name field to amd_ip_funcs (v2)
  drm/amdgpu: Support DRM_MODE_PAGE_FLIP_ASYNC (v2)
  drm/amdgpu/dce11: don't share PLLs on Polaris
  drm/amdgpu: Drop unused parameter for *get_sleep_divider_id_from_clock
  drm/amdgpu: Simplify calculation in *get_sleep_divider_id_from_clock
  drm/amdgpu: Use max macro in *get_sleep_divider_id_from_clock
  drm/amd/powerplay: Use defined constants for minium engine clock
  drm/amdgpu: add missing licenses on a couple of files
  drm/amdgpu: fetch cu_info once at init
  ...

62 files changed, 513 insertions, 395 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 113fd4bf9b64..2a009c398dcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -283,7 +283,8 @@ struct amdgpu_ring_funcs {
 	int (*parse_cs)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 	/* command emit functions */
 	void (*emit_ib)(struct amdgpu_ring *ring,
-			struct amdgpu_ib *ib);
+			struct amdgpu_ib *ib,
+			unsigned vm_id, bool ctx_switch);
 	void (*emit_fence)(struct amdgpu_ring *ring, uint64_t addr,
 			   uint64_t seq, unsigned flags);
 	void (*emit_pipeline_sync)(struct amdgpu_ring *ring);
@@ -367,13 +368,6 @@ struct amdgpu_fence_driver {
 #define AMDGPU_FENCE_FLAG_64BIT         (1 << 0)
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 
-struct amdgpu_user_fence {
-	/* write-back bo */
-	struct amdgpu_bo 	*bo;
-	/* write-back address offset to bo start */
-	uint32_t                offset;
-};
-
 int amdgpu_fence_driver_init(struct amdgpu_device *adev);
 void amdgpu_fence_driver_fini(struct amdgpu_device *adev);
 void amdgpu_fence_driver_force_completion(struct amdgpu_device *adev);
@@ -507,9 +501,10 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 unsigned long amdgpu_gem_timeout(uint64_t timeout_ns);
 struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
-struct drm_gem_object *amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-							struct dma_buf_attachment *attach,
-							struct sg_table *sg);
+struct drm_gem_object *
+amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
+				 struct dma_buf_attachment *attach,
+				 struct sg_table *sg);
 struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 					struct drm_gem_object *gobj,
 					int flags);
@@ -726,6 +721,7 @@ struct amdgpu_flip_work {
 	unsigned			shared_count;
 	struct fence			**shared;
 	struct fence_cb			cb;
+	bool				async;
 };
 
 
@@ -738,17 +734,7 @@ struct amdgpu_ib {
 	uint32_t			length_dw;
 	uint64_t			gpu_addr;
 	uint32_t			*ptr;
-	struct amdgpu_user_fence        *user;
-	struct amdgpu_vm		*vm;
-	unsigned			vm_id;
-	uint64_t			vm_pd_addr;
-	struct amdgpu_ctx		*ctx;
-	uint32_t			gds_base, gds_size;
-	uint32_t			gws_base, gws_size;
-	uint32_t			oa_base, oa_size;
 	uint32_t			flags;
-	/* resulting sequence number */
-	uint64_t			sequence;
 };
 
 enum amdgpu_ring_type {
@@ -762,7 +748,7 @@ enum amdgpu_ring_type {
 extern const struct amd_sched_backend_ops amdgpu_sched_ops;
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
-		     struct amdgpu_job **job);
+		     struct amdgpu_job **job, struct amdgpu_vm *vm);
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 			     struct amdgpu_job **job);
 
@@ -777,7 +763,7 @@ struct amdgpu_ring {
 	struct amdgpu_device		*adev;
 	const struct amdgpu_ring_funcs	*funcs;
 	struct amdgpu_fence_driver	fence_drv;
-	struct amd_gpu_scheduler 	sched;
+	struct amd_gpu_scheduler	sched;
 
 	spinlock_t              fence_lock;
 	struct amdgpu_bo	*ring_obj;
@@ -805,7 +791,7 @@ struct amdgpu_ring {
 	unsigned		wptr_offs;
 	unsigned		next_rptr_offs;
 	unsigned		fence_offs;
-	struct amdgpu_ctx	*current_ctx;
+	uint64_t		current_ctx;
 	enum amdgpu_ring_type	type;
 	char			name[16];
 	unsigned		cond_exe_offs;
@@ -885,6 +871,9 @@ struct amdgpu_vm {
 
 	/* Scheduler entity for page table updates */
 	struct amd_sched_entity	entity;
+
+	/* client id */
+	u64                     client_id;
 };
 
 struct amdgpu_vm_id {
@@ -893,7 +882,7 @@ struct amdgpu_vm_id {
 	struct amdgpu_sync	active;
 	struct fence		*last_flush;
 	struct amdgpu_ring      *last_user;
-	atomic_long_t		owner;
+	atomic64_t		owner;
 
 	uint64_t		pd_gpu_addr;
 	/* last flushed PD/PT update */
@@ -924,6 +913,8 @@ struct amdgpu_vm_manager {
 	struct amdgpu_ring                      *vm_pte_rings[AMDGPU_MAX_RINGS];
 	unsigned				vm_pte_num_rings;
 	atomic_t				vm_pte_next_ring;
+	/* client id counter */
+	atomic64_t				client_counter;
 };
 
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
@@ -1143,6 +1134,12 @@ struct amdgpu_gca_config {
 	uint32_t macrotile_mode_array[16];
 };
 
+struct amdgpu_cu_info {
+	uint32_t number; /* total active CU number */
+	uint32_t ao_cu_mask;
+	uint32_t bitmap[4][4];
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gca_config	config;
@@ -1175,17 +1172,19 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_reg_irq;
 	struct amdgpu_irq_src		priv_inst_irq;
 	/* gfx status */
-	uint32_t gfx_current_status;
+	uint32_t			gfx_current_status;
 	/* ce ram size*/
-	unsigned ce_ram_size;
+	unsigned			ce_ram_size;
+	struct amdgpu_cu_info		cu_info;
 };
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		  unsigned size, struct amdgpu_ib *ib);
-void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, struct fence *f);
+void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
+		    struct fence *f);
 int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		       struct amdgpu_ib *ib, struct fence *last_vm_update,
-		       struct fence **f);
+		       struct amdgpu_job *job, struct fence **f);
 int amdgpu_ib_pool_init(struct amdgpu_device *adev);
 void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
@@ -1210,7 +1209,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring);
 struct amdgpu_cs_chunk {
 	uint32_t		chunk_id;
 	uint32_t		length_dw;
-	uint32_t		*kdata;
+	void			*kdata;
 };
 
 struct amdgpu_cs_parser {
@@ -1241,13 +1240,25 @@ struct amdgpu_cs_parser {
 struct amdgpu_job {
 	struct amd_sched_job    base;
 	struct amdgpu_device	*adev;
+	struct amdgpu_vm	*vm;
 	struct amdgpu_ring	*ring;
 	struct amdgpu_sync	sync;
 	struct amdgpu_ib	*ibs;
 	struct fence		*fence; /* the hw fence */
 	uint32_t		num_ibs;
 	void			*owner;
-	struct amdgpu_user_fence uf;
+	uint64_t		ctx;
+	unsigned		vm_id;
+	uint64_t		vm_pd_addr;
+	uint32_t		gds_base, gds_size;
+	uint32_t		gws_base, gws_size;
+	uint32_t		oa_base, oa_size;
+
+	/* user fence handling */
+	struct amdgpu_bo	*uf_bo;
+	uint32_t		uf_offset;
+	uint64_t		uf_sequence;
+
 };
 #define to_amdgpu_job(sched_job)		\
 		container_of((sched_job), struct amdgpu_job, base)
@@ -1694,7 +1705,7 @@ struct amdgpu_sdma {
 	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
 	struct amdgpu_irq_src	trap_irq;
 	struct amdgpu_irq_src	illegal_inst_irq;
-	int 			num_instances;
+	int			num_instances;
 };
 
 /*
@@ -1787,13 +1798,6 @@ struct amdgpu_allowed_register_entry {
 	bool grbm_indexed;
 };
 
-struct amdgpu_cu_info {
-	uint32_t number; /* total active CU number */
-	uint32_t ao_cu_mask;
-	uint32_t bitmap[4][4];
-};
-
-
 /*
  * ASIC specific functions.
  */
@@ -1811,7 +1815,6 @@ struct amdgpu_asic_funcs {
 	u32 (*get_xclk)(struct amdgpu_device *adev);
 	/* get the gpu clock counter */
 	uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev);
-	int (*get_cu_info)(struct amdgpu_device *adev, struct amdgpu_cu_info *info);
 	/* MM block clocks */
 	int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk);
 	int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk);
@@ -1948,11 +1951,11 @@ struct amdgpu_device {
 	bool				shutdown;
 	bool				need_dma32;
 	bool				accel_working;
-	struct work_struct 		reset_work;
+	struct work_struct		reset_work;
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
 	struct amdgpu_debugfs		debugfs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
-	unsigned 			debugfs_count;
+	unsigned			debugfs_count;
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
@@ -2203,7 +2206,6 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev))
 #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l))
 #define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v)))
-#define amdgpu_asic_get_cu_info(adev, info) (adev)->asic_funcs->get_cu_info((adev), (info))
 #define amdgpu_gart_flush_gpu_tlb(adev, vmid) (adev)->gart.gart_funcs->flush_gpu_tlb((adev), (vmid))
 #define amdgpu_gart_set_pte_pde(adev, pt, idx, addr, flags) (adev)->gart.gart_funcs->set_pte_pde((adev), (pt), (idx), (addr), (flags))
 #define amdgpu_vm_copy_pte(adev, ib, pe, src, count) ((adev)->vm_manager.vm_pte_funcs->copy_pte((ib), (pe), (src), (count)))
@@ -2215,7 +2217,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
-#define amdgpu_ring_emit_ib(r, ib) (r)->funcs->emit_ib((r), (ib))
+#define amdgpu_ring_emit_ib(r, ib, vm_id, c) (r)->funcs->emit_ib((r), (ib), (vm_id), (c))
 #define amdgpu_ring_emit_pipeline_sync(r) (r)->funcs->emit_pipeline_sync((r))
 #define amdgpu_ring_emit_vm_flush(r, vmid, addr) (r)->funcs->emit_vm_flush((r), (vmid), (addr))
 #define amdgpu_ring_emit_fence(r, addr, seq, flags) (r)->funcs->emit_fence((r), (addr), (seq), (flags))
@@ -2238,7 +2240,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_display_hpd_set_polarity(adev, h) (adev)->mode_info.funcs->hpd_set_polarity((adev), (h))
 #define amdgpu_display_hpd_get_gpio_reg(adev) (adev)->mode_info.funcs->hpd_get_gpio_reg((adev))
 #define amdgpu_display_bandwidth_update(adev) (adev)->mode_info.funcs->bandwidth_update((adev))
-#define amdgpu_display_page_flip(adev, crtc, base) (adev)->mode_info.funcs->page_flip((adev), (crtc), (base))
+#define amdgpu_display_page_flip(adev, crtc, base, async) (adev)->mode_info.funcs->page_flip((adev), (crtc), (base), (async))
 #define amdgpu_display_page_flip_get_scanoutpos(adev, crtc, vbl, pos) (adev)->mode_info.funcs->page_flip_get_scanoutpos((adev), (crtc), (vbl), (pos))
 #define amdgpu_display_add_encoder(adev, e, s, c) (adev)->mode_info.funcs->add_encoder((adev), (e), (s), (c))
 #define amdgpu_display_add_connector(adev, ci, sd, ct, ib, coi, h, r) (adev)->mode_info.funcs->add_connector((adev), (ci), (sd), (ct), (ib), (coi), (h), (r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 49838dfe9bda..252edba16e36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -480,6 +480,7 @@ static int acp_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs acp_ip_funcs = {
+	.name = "acp_ip",
 	.early_init = acp_early_init,
 	.late_init = NULL,
 	.sw_init = acp_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index eacd810fc09b..35d0856738ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -263,7 +263,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		for (i = 0; i < args->in.bo_number; ++i) {
 			if (copy_from_user(&info[i], uptr, bytes))
 				goto error_free;
-			
+
 			uptr += args->in.bo_info_size;
 		}
 	}
@@ -271,7 +271,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
 		r = amdgpu_bo_list_create(fpriv, &list, &handle);
-		if (r) 
+		if (r)
 			goto error_free;
 
 		r = amdgpu_bo_list_set(adev, filp, list, info,
@@ -281,7 +281,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 			goto error_free;
 
 		break;
-		
+
 	case AMDGPU_BO_LIST_OP_DESTROY:
 		amdgpu_bo_list_destroy(fpriv, handle);
 		handle = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 490464e39322..199f76baf22c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -793,7 +793,6 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 				struct cgs_system_info *sys_info)
 {
 	CGS_FUNC_ADEV;
-	struct amdgpu_cu_info cu_info;
 
 	if (NULL == sys_info)
 		return -ENODEV;
@@ -818,8 +817,7 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device,
 		sys_info->value = adev->pg_flags;
 		break;
 	case CGS_SYSTEM_INFO_GFX_CU_INFO:
-		amdgpu_asic_get_cu_info(adev, &cu_info);
-		sys_info->value = cu_info.number;
+		sys_info->value = adev->gfx.cu_info.number;
 		break;
 	default:
 		return -ENODEV;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2ebba295d0e4..2bbeeb07c187 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -87,44 +87,42 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 }
 
 static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
-				      struct amdgpu_user_fence *uf,
-				      struct drm_amdgpu_cs_chunk_fence *fence_data)
+				      struct drm_amdgpu_cs_chunk_fence *data,
+				      uint32_t *offset)
 {
 	struct drm_gem_object *gobj;
-	uint32_t handle;
 
-	handle = fence_data->handle;
 	gobj = drm_gem_object_lookup(p->adev->ddev, p->filp,
-				     fence_data->handle);
+				     data->handle);
 	if (gobj == NULL)
 		return -EINVAL;
 
-	uf->bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
-	uf->offset = fence_data->offset;
-
-	if (amdgpu_ttm_tt_get_usermm(uf->bo->tbo.ttm)) {
-		drm_gem_object_unreference_unlocked(gobj);
-		return -EINVAL;
-	}
-
-	p->uf_entry.robj = amdgpu_bo_ref(uf->bo);
+	p->uf_entry.robj = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &p->uf_entry.robj->tbo;
 	p->uf_entry.tv.shared = true;
 	p->uf_entry.user_pages = NULL;
+	*offset = data->offset;
 
 	drm_gem_object_unreference_unlocked(gobj);
+
+	if (amdgpu_ttm_tt_get_usermm(p->uf_entry.robj->tbo.ttm)) {
+		amdgpu_bo_unref(&p->uf_entry.robj);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
 	uint64_t *chunk_array;
-	struct amdgpu_user_fence uf = {};
 	unsigned size, num_ibs = 0;
+	uint32_t uf_offset = 0;
 	int i;
 	int ret;
 
@@ -199,7 +197,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 				goto free_partial_kdata;
 			}
 
-			ret = amdgpu_cs_user_fence_chunk(p, &uf, (void *)p->chunks[i].kdata);
+			ret = amdgpu_cs_user_fence_chunk(p, p->chunks[i].kdata,
+							 &uf_offset);
 			if (ret)
 				goto free_partial_kdata;
 
@@ -214,11 +213,14 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 		}
 	}
 
-	ret = amdgpu_job_alloc(p->adev, num_ibs, &p->job);
+	ret = amdgpu_job_alloc(p->adev, num_ibs, &p->job, vm);
 	if (ret)
 		goto free_all_kdata;
 
-	p->job->uf = uf;
+	if (p->uf_entry.robj) {
+		p->job->uf_bo = amdgpu_bo_ref(p->uf_entry.robj);
+		p->job->uf_offset = uf_offset;
+	}
 
 	kfree(chunk_array);
 	return 0;
@@ -376,7 +378,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
 
-	if (p->job->uf.bo)
+	if (p->uf_entry.robj)
 		list_add(&p->uf_entry.tv.head, &p->validated);
 
 	if (need_mmap_lock)
@@ -472,6 +474,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		goto error_validate;
 
 	if (p->bo_list) {
+		struct amdgpu_bo *gds = p->bo_list->gds_obj;
+		struct amdgpu_bo *gws = p->bo_list->gws_obj;
+		struct amdgpu_bo *oa = p->bo_list->oa_obj;
 		struct amdgpu_vm *vm = &fpriv->vm;
 		unsigned i;
 
@@ -480,6 +485,19 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 			p->bo_list->array[i].bo_va = amdgpu_vm_bo_find(vm, bo);
 		}
+
+		if (gds) {
+			p->job->gds_base = amdgpu_bo_gpu_offset(gds);
+			p->job->gds_size = amdgpu_bo_size(gds);
+		}
+		if (gws) {
+			p->job->gws_base = amdgpu_bo_gpu_offset(gws);
+			p->job->gws_size = amdgpu_bo_size(gws);
+		}
+		if (oa) {
+			p->job->oa_base = amdgpu_bo_gpu_offset(oa);
+			p->job->oa_size = amdgpu_bo_size(oa);
+		}
 	}
 
 error_validate:
@@ -740,41 +758,14 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 		ib->length_dw = chunk_ib->ib_bytes / 4;
 		ib->flags = chunk_ib->flags;
-		ib->ctx = parser->ctx;
 		j++;
 	}
 
-	/* add GDS resources to first IB */
-	if (parser->bo_list) {
-		struct amdgpu_bo *gds = parser->bo_list->gds_obj;
-		struct amdgpu_bo *gws = parser->bo_list->gws_obj;
-		struct amdgpu_bo *oa = parser->bo_list->oa_obj;
-		struct amdgpu_ib *ib = &parser->job->ibs[0];
-
-		if (gds) {
-			ib->gds_base = amdgpu_bo_gpu_offset(gds);
-			ib->gds_size = amdgpu_bo_size(gds);
-		}
-		if (gws) {
-			ib->gws_base = amdgpu_bo_gpu_offset(gws);
-			ib->gws_size = amdgpu_bo_size(gws);
-		}
-		if (oa) {
-			ib->oa_base = amdgpu_bo_gpu_offset(oa);
-			ib->oa_size = amdgpu_bo_size(oa);
-		}
-	}
-	/* wrap the last IB with user fence */
-	if (parser->job->uf.bo) {
-		struct amdgpu_ib *ib = &parser->job->ibs[parser->job->num_ibs - 1];
-
-		/* UVD & VCE fw doesn't support user fences */
-		if (parser->job->ring->type == AMDGPU_RING_TYPE_UVD ||
-		    parser->job->ring->type == AMDGPU_RING_TYPE_VCE)
-			return -EINVAL;
-
-		ib->user = &parser->job->uf;
-	}
+	/* UVD & VCE fw doesn't support user fences */
+	if (parser->job->uf_bo && (
+	    parser->job->ring->type == AMDGPU_RING_TYPE_UVD ||
+	    parser->job->ring->type == AMDGPU_RING_TYPE_VCE))
+		return -EINVAL;
 
 	return 0;
 }
@@ -839,6 +830,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_ring *ring = p->job->ring;
+	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	struct fence *fence;
 	struct amdgpu_job *job;
 	int r;
@@ -847,19 +839,19 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	p->job = NULL;
 
 	r = amd_sched_job_init(&job->base, &ring->sched,
-						&p->ctx->rings[ring->idx].entity,
-						amdgpu_job_timeout_func,
-						amdgpu_job_free_func,
-						p->filp, &fence);
+			       entity, amdgpu_job_timeout_func,
+			       amdgpu_job_free_func,
+			       p->filp, &fence);
 	if (r) {
 		amdgpu_job_free(job);
 		return r;
 	}
 
 	job->owner = p->filp;
+	job->ctx = entity->fence_context;
 	p->fence = fence_get(fence);
 	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, fence);
-	job->ibs[job->num_ibs - 1].sequence = cs->out.handle;
+	job->uf_sequence = cs->out.handle;
 
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 778330529ff5..bb8b149786d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -348,7 +348,7 @@ static int amdgpu_doorbell_init(struct amdgpu_device *adev)
 	adev->doorbell.base = pci_resource_start(adev->pdev, 2);
 	adev->doorbell.size = pci_resource_len(adev->pdev, 2);
 
-	adev->doorbell.num_doorbells = min_t(u32, adev->doorbell.size / sizeof(u32), 
+	adev->doorbell.num_doorbells = min_t(u32, adev->doorbell.size / sizeof(u32),
 					     AMDGPU_DOORBELL_MAX_ASSIGNMENT+1);
 	if (adev->doorbell.num_doorbells == 0)
 		return -EINVAL;
@@ -1196,7 +1196,7 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 				if (r == -ENOENT) {
 					adev->ip_block_status[i].valid = false;
 				} else if (r) {
-					DRM_ERROR("early_init %d failed %d\n", i, r);
+					DRM_ERROR("early_init of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 					return r;
 				} else {
 					adev->ip_block_status[i].valid = true;
@@ -1219,7 +1219,7 @@ static int amdgpu_init(struct amdgpu_device *adev)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_init((void *)adev);
 		if (r) {
-			DRM_ERROR("sw_init %d failed %d\n", i, r);
+			DRM_ERROR("sw_init of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			return r;
 		}
 		adev->ip_block_status[i].sw = true;
@@ -1252,7 +1252,7 @@ static int amdgpu_init(struct amdgpu_device *adev)
 			continue;
 		r = adev->ip_blocks[i].funcs->hw_init((void *)adev);
 		if (r) {
-			DRM_ERROR("hw_init %d failed %d\n", i, r);
+			DRM_ERROR("hw_init of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			return r;
 		}
 		adev->ip_block_status[i].hw = true;
@@ -1272,13 +1272,13 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
 								    AMD_CG_STATE_GATE);
 		if (r) {
-			DRM_ERROR("set_clockgating_state(gate) %d failed %d\n", i, r);
+			DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			return r;
 		}
 		if (adev->ip_blocks[i].funcs->late_init) {
 			r = adev->ip_blocks[i].funcs->late_init((void *)adev);
 			if (r) {
-				DRM_ERROR("late_init %d failed %d\n", i, r);
+				DRM_ERROR("late_init of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 				return r;
 			}
 		}
@@ -1302,13 +1302,13 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
 								    AMD_CG_STATE_UNGATE);
 		if (r) {
-			DRM_ERROR("set_clockgating_state(ungate) %d failed %d\n", i, r);
+			DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			return r;
 		}
 		r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
 		/* XXX handle errors */
 		if (r) {
-			DRM_DEBUG("hw_fini %d failed %d\n", i, r);
+			DRM_DEBUG("hw_fini of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 		}
 		adev->ip_block_status[i].hw = false;
 	}
@@ -1319,7 +1319,7 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 		r = adev->ip_blocks[i].funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
 		if (r) {
-			DRM_DEBUG("sw_fini %d failed %d\n", i, r);
+			DRM_DEBUG("sw_fini of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 		}
 		adev->ip_block_status[i].sw = false;
 		adev->ip_block_status[i].valid = false;
@@ -1347,14 +1347,14 @@ static int amdgpu_suspend(struct amdgpu_device *adev)
 			r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
 									    AMD_CG_STATE_UNGATE);
 			if (r) {
-				DRM_ERROR("set_clockgating_state(ungate) %d failed %d\n", i, r);
+				DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			}
 		}
 		/* XXX handle errors */
 		r = adev->ip_blocks[i].funcs->suspend(adev);
 		/* XXX handle errors */
 		if (r) {
-			DRM_ERROR("suspend %d failed %d\n", i, r);
+			DRM_ERROR("suspend of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 		}
 	}
 
@@ -1370,7 +1370,7 @@ static int amdgpu_resume(struct amdgpu_device *adev)
 			continue;
 		r = adev->ip_blocks[i].funcs->resume(adev);
 		if (r) {
-			DRM_ERROR("resume %d failed %d\n", i, r);
+			DRM_ERROR("resume of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
 			return r;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index c835abe65df3..726803069fef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -132,7 +132,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 				 vblank->linedur_ns / 1000, stat, vpos, hpos);
 
 	/* Do the flip (mmio) */
-	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
+	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base, work->async);
 
 	/* Set the flip status */
 	amdgpuCrtc->pflip_status = AMDGPU_FLIP_SUBMITTED;
@@ -197,6 +197,7 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	work->event = event;
 	work->adev = adev;
 	work->crtc_id = amdgpu_crtc->crtc_id;
+	work->async = (page_flip_flags & DRM_MODE_PAGE_FLIP_ASYNC) != 0;
 
 	/* schedule unpin of the old buffer */
 	old_amdgpu_fb = to_amdgpu_framebuffer(crtc->primary->fb);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
index c3f4e85594ff..503d54098128 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
@@ -43,7 +43,7 @@ struct amdgpu_ring;
 struct amdgpu_bo;
 
 struct amdgpu_gds_asic_info {
-	uint32_t 	total_size;
+	uint32_t	total_size;
 	uint32_t	gfx_partition_size;
 	uint32_t	cs_partition_size;
 };
@@ -52,8 +52,8 @@ struct amdgpu_gds {
 	struct amdgpu_gds_asic_info	mem;
 	struct amdgpu_gds_asic_info	gws;
 	struct amdgpu_gds_asic_info	oa;
-	/* At present, GDS, GWS and OA resources for gfx (graphics) 
-	 * is always pre-allocated and available for graphics operation. 
+	/* At present, GDS, GWS and OA resources for gfx (graphics)
+	 * is always pre-allocated and available for graphics operation.
 	 * Such resource is shared between all gfx clients.
 	 * TODO: move this operation to user space
 	 * */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 0129617a7962..34e35423b78e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -74,9 +74,6 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
 	}
 
-	ib->vm = vm;
-	ib->vm_id = 0;
-
 	return 0;
 }
 
@@ -89,7 +86,8 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  *
  * Free an IB (all asics).
  */
-void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, struct fence *f)
+void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
+		    struct fence *f)
 {
 	amdgpu_sa_bo_free(adev, &ib->sa_bo, f);
 }
@@ -117,29 +115,37 @@ void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, struct fen
  */
 int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		       struct amdgpu_ib *ibs, struct fence *last_vm_update,
-		       struct fence **f)
+		       struct amdgpu_job *job, struct fence **f)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib *ib = &ibs[0];
-	struct amdgpu_ctx *ctx, *old_ctx;
+	bool skip_preamble, need_ctx_switch;
+	unsigned patch_offset = ~0;
 	struct amdgpu_vm *vm;
 	struct fence *hwf;
-	unsigned i, patch_offset = ~0;
+	uint64_t ctx;
 
+	unsigned i;
 	int r = 0;
 
 	if (num_ibs == 0)
 		return -EINVAL;
 
-	ctx = ibs->ctx;
-	vm = ibs->vm;
+	/* ring tests don't use a job */
+	if (job) {
+		vm = job->vm;
+		ctx = job->ctx;
+	} else {
+		vm = NULL;
+		ctx = 0;
+	}
 
 	if (!ring->ready) {
 		dev_err(adev->dev, "couldn't schedule ib\n");
 		return -EINVAL;
 	}
 
-	if (vm && !ibs->vm_id) {
+	if (vm && !job->vm_id) {
 		dev_err(adev->dev, "VM IB without ID\n");
 		return -EINVAL;
 	}
@@ -154,58 +160,54 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		patch_offset = amdgpu_ring_init_cond_exec(ring);
 
 	if (vm) {
-		/* do context switch */
-		r = amdgpu_vm_flush(ring, ib->vm_id, ib->vm_pd_addr,
-				    ib->gds_base, ib->gds_size,
-				    ib->gws_base, ib->gws_size,
-				    ib->oa_base, ib->oa_size);
+		r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr,
+				    job->gds_base, job->gds_size,
+				    job->gws_base, job->gws_size,
+				    job->oa_base, job->oa_size);
 		if (r) {
 			amdgpu_ring_undo(ring);
 			return r;
 		}
-
-		if (ring->funcs->emit_hdp_flush)
-			amdgpu_ring_emit_hdp_flush(ring);
 	}
 
+	if (ring->funcs->emit_hdp_flush)
+		amdgpu_ring_emit_hdp_flush(ring);
+
 	/* always set cond_exec_polling to CONTINUE */
 	*ring->cond_exe_cpu_addr = 1;
 
-	old_ctx = ring->current_ctx;
+	skip_preamble = ring->current_ctx == ctx;
+	need_ctx_switch = ring->current_ctx != ctx;
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
 
-		if (ib->ctx != ctx || ib->vm != vm) {
-			ring->current_ctx = old_ctx;
-			if (ib->vm_id)
-				amdgpu_vm_reset_id(adev, ib->vm_id);
-			amdgpu_ring_undo(ring);
-			return -EINVAL;
-		}
-		amdgpu_ring_emit_ib(ring, ib);
-		ring->current_ctx = ctx;
-	}
+		/* drop preamble IBs if we don't have a context switch */
+		if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && skip_preamble)
+			continue;
 
-	if (vm) {
-		if (ring->funcs->emit_hdp_invalidate)
-			amdgpu_ring_emit_hdp_invalidate(ring);
+		amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0,
+				    need_ctx_switch);
+		need_ctx_switch = false;
 	}
 
+	if (ring->funcs->emit_hdp_invalidate)
+		amdgpu_ring_emit_hdp_invalidate(ring);
+
 	r = amdgpu_fence_emit(ring, &hwf);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
-		ring->current_ctx = old_ctx;
-		if (ib->vm_id)
-			amdgpu_vm_reset_id(adev, ib->vm_id);
+		if (job && job->vm_id)
+			amdgpu_vm_reset_id(adev, job->vm_id);
 		amdgpu_ring_undo(ring);
 		return r;
 	}
 
 	/* wrap the last IB with fence */
-	if (ib->user) {
-		uint64_t addr = amdgpu_bo_gpu_offset(ib->user->bo);
-		addr += ib->user->offset;
-		amdgpu_ring_emit_fence(ring, addr, ib->sequence,
+	if (job && job->uf_bo) {
+		uint64_t addr = amdgpu_bo_gpu_offset(job->uf_bo);
+
+		addr += job->uf_offset;
+		amdgpu_ring_emit_fence(ring, addr, job->uf_sequence,
 				       AMDGPU_FENCE_FLAG_64BIT);
 	}
 
@@ -215,6 +217,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
+	ring->current_ctx = ctx;
 	amdgpu_ring_commit(ring);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4eea2a18d8bb..f0dafa514fe4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -46,7 +46,7 @@ void amdgpu_job_timeout_func(struct work_struct *work)
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
-		     struct amdgpu_job **job)
+		     struct amdgpu_job **job, struct amdgpu_vm *vm)
 {
 	size_t size = sizeof(struct amdgpu_job);
 
@@ -60,6 +60,7 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 		return -ENOMEM;
 
 	(*job)->adev = adev;
+	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
 	INIT_WORK(&(*job)->base.work_free_job, amdgpu_job_free_handler);
@@ -74,7 +75,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 {
 	int r;
 
-	r = amdgpu_job_alloc(adev, 1, job);
+	r = amdgpu_job_alloc(adev, 1, job, NULL);
 	if (r)
 		return r;
 
@@ -96,7 +97,7 @@ void amdgpu_job_free(struct amdgpu_job *job)
 		amdgpu_sa_bo_free(job->adev, &job->ibs[i].sa_bo, f);
 	fence_put(job->fence);
 
-	amdgpu_bo_unref(&job->uf.bo);
+	amdgpu_bo_unref(&job->uf_bo);
 	amdgpu_sync_free(&job->sync);
 
 	if (!job->base.use_sched)
@@ -121,14 +122,13 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		return -EINVAL;
 
 	r = amd_sched_job_init(&job->base, &ring->sched,
-							entity,
-							amdgpu_job_timeout_func,
-							amdgpu_job_free_func,
-							owner, &fence);
+			       entity, amdgpu_job_timeout_func,
+			       amdgpu_job_free_func, owner, &fence);
 	if (r)
 		return r;
 
 	job->owner = owner;
+	job->ctx = entity->fence_context;
 	*f = fence_get(fence);
 	amd_sched_entity_push_job(&job->base);
 
@@ -138,27 +138,19 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job)
 {
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
-	struct amdgpu_vm *vm = job->ibs->vm;
+	struct amdgpu_vm *vm = job->vm;
 
 	struct fence *fence = amdgpu_sync_get_fence(&job->sync);
 
-	if (fence == NULL && vm && !job->ibs->vm_id) {
+	if (fence == NULL && vm && !job->vm_id) {
 		struct amdgpu_ring *ring = job->ring;
-		unsigned i, vm_id;
-		uint64_t vm_pd_addr;
 		int r;
 
 		r = amdgpu_vm_grab_id(vm, ring, &job->sync,
 				      &job->base.s_fence->base,
-				      &vm_id, &vm_pd_addr);
+				      &job->vm_id, &job->vm_pd_addr);
 		if (r)
 			DRM_ERROR("Error getting VM ID (%d)\n", r);
-		else {
-			for (i = 0; i < job->num_ibs; ++i) {
-				job->ibs[i].vm_id = vm_id;
-				job->ibs[i].vm_pd_addr = vm_pd_addr;
-			}
-		}
 
 		fence = amdgpu_sync_get_fence(&job->sync);
 	}
@@ -186,7 +178,7 @@ static struct fence *amdgpu_job_run(struct amd_sched_job *sched_job)
 
 	trace_amdgpu_sched_run_job(job);
 	r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs,
-			       job->sync.last_vm_update, &fence);
+			       job->sync.last_vm_update, job, &fence);
 	if (r) {
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 7db271278e70..40a23704a981 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -427,7 +427,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	}
 	case AMDGPU_INFO_DEV_INFO: {
 		struct drm_amdgpu_info_device dev_info = {};
-		struct amdgpu_cu_info cu_info;
 
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
@@ -461,11 +460,11 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 					     AMDGPU_GPU_PAGE_SIZE;
 		dev_info.gart_page_size = AMDGPU_GPU_PAGE_SIZE;
 
-		amdgpu_asic_get_cu_info(adev, &cu_info);
-		dev_info.cu_active_number = cu_info.number;
-		dev_info.cu_ao_mask = cu_info.ao_cu_mask;
+		dev_info.cu_active_number = adev->gfx.cu_info.number;
+		dev_info.cu_ao_mask = adev->gfx.cu_info.ao_cu_mask;
 		dev_info.ce_ram_size = adev->gfx.ce_ram_size;
-		memcpy(&dev_info.cu_bitmap[0], &cu_info.bitmap[0], sizeof(cu_info.bitmap));
+		memcpy(&dev_info.cu_bitmap[0], &adev->gfx.cu_info.bitmap[0],
+		       sizeof(adev->gfx.cu_info.bitmap));
 		dev_info.vram_type = adev->mc.vram_type;
 		dev_info.vram_bit_width = adev->mc.vram_width;
 		dev_info.vce_harvest_config = adev->vce.harvest_config;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 81bd964d3dfc..6b1d7d306564 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -283,7 +283,7 @@ struct amdgpu_display_funcs {
 	u32 (*hpd_get_gpio_reg)(struct amdgpu_device *adev);
 	/* pageflipping */
 	void (*page_flip)(struct amdgpu_device *adev,
-			 int crtc_id, u64 crtc_base);
+			  int crtc_id, u64 crtc_base, bool async);
 	int (*page_flip_get_scanoutpos)(struct amdgpu_device *adev, int crtc,
 					u32 *vbl, u32 *position);
 	/* display topology setup */
@@ -530,7 +530,7 @@ struct amdgpu_framebuffer {
 				((em) == ATOM_ENCODER_MODE_DP_MST))
 
 /* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */
-#define USE_REAL_VBLANKSTART 		(1 << 30)
+#define USE_REAL_VBLANKSTART		(1 << 30)
 #define GET_DISTANCE_TO_VBLANKSTART	(1 << 31)
 
 void amdgpu_link_encoder_connector(struct drm_device *dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index be565955bcc7..6bd961fb43dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -304,6 +304,7 @@ static int amdgpu_pp_soft_reset(void *handle)
 }
 
 const struct amd_ip_funcs amdgpu_pp_ip_funcs = {
+	.name = "amdgpu_powerplay",
 	.early_init = amdgpu_pp_early_init,
 	.late_init = amdgpu_pp_late_init,
 	.sw_init = amdgpu_pp_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index be6388f73ba2..7700dc22f243 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -57,9 +57,10 @@ void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 	ttm_bo_kunmap(&bo->dma_buf_vmap);
 }
 
-struct drm_gem_object *amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-							struct dma_buf_attachment *attach,
-							struct sg_table *sg)
+struct drm_gem_object *
+amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
+				 struct dma_buf_attachment *attach,
+				 struct sg_table *sg)
 {
 	struct reservation_object *resv = attach->dmabuf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index abda242980ba..01abfc21b4a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -41,13 +41,15 @@
 
 /* 1 second timeout */
 #define UVD_IDLE_TIMEOUT_MS	1000
+/* Polaris10/11 firmware version */
+#define FW_1_66_16 ((1 << 24) | (66 << 16) | (16 << 8))
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
 #define FIRMWARE_BONAIRE	"radeon/bonaire_uvd.bin"
-#define FIRMWARE_KABINI 	"radeon/kabini_uvd.bin"
-#define FIRMWARE_KAVERI 	"radeon/kaveri_uvd.bin"
-#define FIRMWARE_HAWAII 	"radeon/hawaii_uvd.bin"
+#define FIRMWARE_KABINI	"radeon/kabini_uvd.bin"
+#define FIRMWARE_KAVERI	"radeon/kaveri_uvd.bin"
+#define FIRMWARE_HAWAII	"radeon/hawaii_uvd.bin"
 #define FIRMWARE_MULLINS	"radeon/mullins_uvd.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_uvd.bin"
@@ -184,6 +186,12 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
 				(family_id << 8));
 
+	if ((adev->asic_type == CHIP_POLARIS10 ||
+	     adev->asic_type == CHIP_POLARIS11) &&
+	    (adev->uvd.fw_version < FW_1_66_16))
+		DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
+			  version_major, version_minor);
+
 	bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
 		  +  AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE
 		  +  AMDGPU_UVD_SESSION_SIZE * adev->uvd.max_handles;
@@ -414,7 +422,8 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
  *
  * Peek into the decode message and calculate the necessary buffer sizes.
  */
-static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[])
+static int amdgpu_uvd_cs_msg_decode(struct amdgpu_device *adev, uint32_t *msg,
+	unsigned buf_sizes[])
 {
 	unsigned stream_type = msg[4];
 	unsigned width = msg[6];
@@ -436,7 +445,6 @@ static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[])
 
 	switch (stream_type) {
 	case 0: /* H264 */
-	case 7: /* H264 Perf */
 		switch(level) {
 		case 30:
 			num_dpb_buffer = 8100 / fs_in_mb;
@@ -514,6 +522,54 @@ static int amdgpu_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[])
 		min_dpb_size += ALIGN(width_in_mb * height_in_mb * 32, 64);
 		break;
 
+	case 7: /* H264 Perf */
+		switch(level) {
+		case 30:
+			num_dpb_buffer = 8100 / fs_in_mb;
+			break;
+		case 31:
+			num_dpb_buffer = 18000 / fs_in_mb;
+			break;
+		case 32:
+			num_dpb_buffer = 20480 / fs_in_mb;
+			break;
+		case 41:
+			num_dpb_buffer = 32768 / fs_in_mb;
+			break;
+		case 42:
+			num_dpb_buffer = 34816 / fs_in_mb;
+			break;
+		case 50:
+			num_dpb_buffer = 110400 / fs_in_mb;
+			break;
+		case 51:
+			num_dpb_buffer = 184320 / fs_in_mb;
+			break;
+		default:
+			num_dpb_buffer = 184320 / fs_in_mb;
+			break;
+		}
+		num_dpb_buffer++;
+		if (num_dpb_buffer > 17)
+			num_dpb_buffer = 17;
+
+		/* reference picture buffer */
+		min_dpb_size = image_size * num_dpb_buffer;
+
+		if (adev->asic_type < CHIP_POLARIS10){
+			/* macroblock context buffer */
+			min_dpb_size +=
+				width_in_mb * height_in_mb * num_dpb_buffer * 192;
+
+			/* IT surface buffer */
+			min_dpb_size += width_in_mb * height_in_mb * 32;
+		} else {
+			/* macroblock context buffer */
+			min_ctx_size =
+				width_in_mb * height_in_mb * num_dpb_buffer * 192;
+		}
+		break;
+
 	case 16: /* H265 */
 		image_size = (ALIGN(width, 16) * ALIGN(height, 16) * 3) / 2;
 		image_size = ALIGN(image_size, 256);
@@ -609,7 +665,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 	case 1:
 		/* it's a decode msg, calc buffer sizes */
-		r = amdgpu_uvd_cs_msg_decode(msg, ctx->buf_sizes);
+		r = amdgpu_uvd_cs_msg_decode(adev, msg, ctx->buf_sizes);
 		amdgpu_bo_kunmap(bo);
 		if (r)
 			return r;
@@ -910,7 +966,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	ib->length_dw = 16;
 
 	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+		r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
 		job->fence = f;
 		if (r)
 			goto err_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 22a4d96fedb7..875626a2eccb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -41,9 +41,9 @@
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
 #define FIRMWARE_BONAIRE	"radeon/bonaire_vce.bin"
-#define FIRMWARE_KABINI 	"radeon/kabini_vce.bin"
-#define FIRMWARE_KAVERI 	"radeon/kaveri_vce.bin"
-#define FIRMWARE_HAWAII 	"radeon/hawaii_vce.bin"
+#define FIRMWARE_KABINI	"radeon/kabini_vce.bin"
+#define FIRMWARE_KAVERI	"radeon/kaveri_vce.bin"
+#define FIRMWARE_HAWAII	"radeon/hawaii_vce.bin"
 #define FIRMWARE_MULLINS	"radeon/mullins_vce.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_vce.bin"
@@ -436,7 +436,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
 	job->fence = f;
 	if (r)
 		goto err;
@@ -498,7 +498,7 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 		ib->ptr[i] = 0x0;
 
 	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+		r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f);
 		job->fence = f;
 		if (r)
 			goto err;
@@ -762,7 +762,8 @@ out:
  * @ib: the IB to execute
  *
  */
-void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
+void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib,
+			     unsigned vm_id, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, VCE_CMD_IB);
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index ef99d2370182..f40cf761c66f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -34,7 +34,8 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 			       bool direct, struct fence **fence);
 void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp);
 int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx);
-void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
+void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib,
+			     unsigned vm_id, bool ctx_switch);
 void amdgpu_vce_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
 				unsigned flags);
 int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 856116a874bb..ea708cb94862 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -185,7 +185,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		if (!id)
 			continue;
 
-		if (atomic_long_read(&id->owner) != (long)vm)
+		if (atomic64_read(&id->owner) != vm->client_id)
 			continue;
 
 		if (pd_addr != id->pd_gpu_addr)
@@ -261,7 +261,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 
 	list_move_tail(&id->list, &adev->vm_manager.ids_lru);
 	id->last_user = ring;
-	atomic_long_set(&id->owner, (long)vm);
+	atomic64_set(&id->owner, vm->client_id);
 	vm->ids[ring->idx] = id;
 
 	*vm_id = id - adev->vm_manager.ids;
@@ -300,10 +300,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring,
 	int r;
 
 	if (ring->funcs->emit_pipeline_sync && (
-	    pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed))
+	    pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed ||
+		    ring->type == AMDGPU_RING_TYPE_COMPUTE))
 		amdgpu_ring_emit_pipeline_sync(ring);
 
-	if (pd_addr != AMDGPU_VM_NO_FLUSH) {
+	if (ring->funcs->emit_vm_flush &&
+	    pd_addr != AMDGPU_VM_NO_FLUSH) {
 		struct fence *fence;
 
 		trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id);
@@ -1386,6 +1388,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
 		vm->ids[i] = NULL;
 	vm->va = RB_ROOT;
+	vm->client_id = atomic64_inc_return(&adev->vm_manager.client_counter);
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->cleared);
@@ -1477,15 +1480,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_bo_unref(&vm->page_directory);
 	fence_put(vm->page_directory_fence);
-
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
-		struct amdgpu_vm_id *id = vm->ids[i];
-
-		if (!id)
-			continue;
-
-		atomic_long_cmpxchg(&id->owner, (long)vm, 0);
-	}
 }
 
 /**
@@ -1510,6 +1504,7 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	}
 
 	atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
+	atomic64_set(&adev->vm_manager.client_counter, 0);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.h b/drivers/gpu/drm/amd/amdgpu/atom.h
index fece8f45dc7a..49daf6d723e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.h
+++ b/drivers/gpu/drm/amd/amdgpu/atom.h
@@ -92,7 +92,7 @@
 #define ATOM_WS_AND_MASK	0x45
 #define ATOM_WS_FB_WINDOW	0x46
 #define ATOM_WS_ATTRIBUTES	0x47
-#define ATOM_WS_REGPTR  	0x48
+#define ATOM_WS_REGPTR		0x48
 
 #define ATOM_IIO_NOP		0
 #define ATOM_IIO_START		1
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 90f83b21b38c..ea407db1fbcf 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -2549,19 +2549,17 @@ static int ci_get_dependency_volt_by_clk(struct amdgpu_device *adev,
 	return 0;
 }
 
-static u8 ci_get_sleep_divider_id_from_clock(struct amdgpu_device *adev,
-					     u32 sclk, u32 min_sclk_in_sr)
+static u8 ci_get_sleep_divider_id_from_clock(u32 sclk, u32 min_sclk_in_sr)
 {
 	u32 i;
 	u32 tmp;
-	u32 min = (min_sclk_in_sr > CISLAND_MINIMUM_ENGINE_CLOCK) ?
-		min_sclk_in_sr : CISLAND_MINIMUM_ENGINE_CLOCK;
+	u32 min = max(min_sclk_in_sr, (u32)CISLAND_MINIMUM_ENGINE_CLOCK);
 
 	if (sclk < min)
 		return 0;
 
 	for (i = CISLAND_MAX_DEEPSLEEP_DIVIDER_ID;  ; i--) {
-		tmp = sclk / (1 << i);
+		tmp = sclk >> i;
 		if (tmp >= min || i == 0)
 			break;
 	}
@@ -3358,8 +3356,7 @@ static int ci_populate_single_graphic_level(struct amdgpu_device *adev,
 	graphic_level->PowerThrottle = 0;
 
 	if (pi->caps_sclk_ds)
-		graphic_level->DeepSleepDivId = ci_get_sleep_divider_id_from_clock(adev,
-										   engine_clock,
+		graphic_level->DeepSleepDivId = ci_get_sleep_divider_id_from_clock(engine_clock,
 										   CISLAND_MINIMUM_ENGINE_CLOCK);
 
 	graphic_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW;
@@ -6363,7 +6360,7 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev,
 }
 
 static int ci_dpm_process_interrupt(struct amdgpu_device *adev,
-				    struct amdgpu_irq_src *source, 
+				    struct amdgpu_irq_src *source,
 				    struct amdgpu_iv_entry *entry)
 {
 	bool queue_thermal = false;
@@ -6405,6 +6402,7 @@ static int ci_dpm_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs ci_dpm_ip_funcs = {
+	.name = "ci_dpm",
 	.early_init = ci_dpm_early_init,
 	.late_init = ci_dpm_late_init,
 	.sw_init = ci_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index c6127d66de11..07bc795a4ca9 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -2007,7 +2007,6 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_xclk = &cik_get_xclk,
 	.set_uvd_clocks = &cik_set_uvd_clocks,
 	.set_vce_clocks = &cik_set_vce_clocks,
-	.get_cu_info = &gfx_v7_0_get_cu_info,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle,
@@ -2233,6 +2232,7 @@ static int cik_common_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs cik_common_ip_funcs = {
+	.name = "cik_common",
 	.early_init = cik_common_early_init,
 	.late_init = NULL,
 	.sw_init = cik_common_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_ih.c b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
index f2f14fe26784..845c21b1b2ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -243,7 +243,7 @@ static void cik_ih_decode_iv(struct amdgpu_device *adev,
 	/* wptr/rptr are in bytes! */
 	u32 ring_index = adev->irq.ih.rptr >> 2;
 	uint32_t dw[4];
-	
+
 	dw[0] = le32_to_cpu(adev->irq.ih.ring[ring_index + 0]);
 	dw[1] = le32_to_cpu(adev->irq.ih.ring[ring_index + 1]);
 	dw[2] = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]);
@@ -415,6 +415,7 @@ static int cik_ih_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs cik_ih_ip_funcs = {
+	.name = "cik_ih",
 	.early_init = cik_ih_early_init,
 	.late_init = NULL,
 	.sw_init = cik_ih_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index b7ed9d376001..518dca43b133 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -210,9 +210,10 @@ static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  * Schedule an IB in the DMA ring (CIK).
  */
 static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
-			   struct amdgpu_ib *ib)
+				  struct amdgpu_ib *ib,
+				  unsigned vm_id, bool ctx_switch)
 {
-	u32 extra_bits = ib->vm_id & 0xf;
+	u32 extra_bits = vm_id & 0xf;
 	u32 next_rptr = ring->wptr + 5;
 
 	while ((next_rptr & 7) != 4)
@@ -643,7 +644,7 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring)
 	ib.ptr[3] = 1;
 	ib.ptr[4] = 0xDEADBEEF;
 	ib.length_dw = 5;
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r)
 		goto err1;
 
@@ -1223,6 +1224,7 @@ static int cik_sdma_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs cik_sdma_ip_funcs = {
+	.name = "cik_sdma",
 	.early_init = cik_sdma_early_init,
 	.late_init = NULL,
 	.sw_init = cik_sdma_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cikd.h b/drivers/gpu/drm/amd/amdgpu/cikd.h
index 60d4493206dd..c4f6f00d62bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/cikd.h
+++ b/drivers/gpu/drm/amd/amdgpu/cikd.h
@@ -190,8 +190,8 @@
 #       define MACRO_TILE_ASPECT(x)				((x) << 4)
 #       define NUM_BANKS(x)					((x) << 6)
 
-#define		MSG_ENTER_RLC_SAFE_MODE      			1
-#define		MSG_EXIT_RLC_SAFE_MODE      			0
+#define		MSG_ENTER_RLC_SAFE_MODE			1
+#define		MSG_EXIT_RLC_SAFE_MODE			0
 
 /*
  * PM4
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index bf1847b28d9c..fa4449e126e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -2230,6 +2230,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 }
 
 const struct amd_ip_funcs cz_dpm_ip_funcs = {
+	.name = "cz_dpm",
 	.early_init = cz_dpm_early_init,
 	.late_init = cz_dpm_late_init,
 	.sw_init = cz_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 23bd9122b15d..863cb16f6126 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -222,7 +222,7 @@ static void cz_ih_decode_iv(struct amdgpu_device *adev,
 	/* wptr/rptr are in bytes! */
 	u32 ring_index = adev->irq.ih.rptr >> 2;
 	uint32_t dw[4];
-	
+
 	dw[0] = le32_to_cpu(adev->irq.ih.ring[ring_index + 0]);
 	dw[1] = le32_to_cpu(adev->irq.ih.ring[ring_index + 1]);
 	dw[2] = le32_to_cpu(adev->irq.ih.ring[ring_index + 2]);
@@ -396,6 +396,7 @@ static int cz_ih_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs cz_ih_ip_funcs = {
+	.name = "cz_ih",
 	.early_init = cz_ih_early_init,
 	.late_init = NULL,
 	.sw_init = cz_ih_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_smumgr.h b/drivers/gpu/drm/amd/amdgpu/cz_smumgr.h
index 924d355b4e2c..026342fcf0f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_smumgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/cz_smumgr.h
@@ -77,7 +77,7 @@ struct cz_smu_private_data {
 	uint8_t		driver_buffer_length;
 	uint8_t		scratch_buffer_length;
 	uint16_t	toc_entry_used_count;
-	uint16_t 	toc_entry_initialize_index;
+	uint16_t	toc_entry_initialize_index;
 	uint16_t	toc_entry_power_profiling_index;
 	uint16_t	toc_entry_aram;
 	uint16_t	toc_entry_ih_register_restore_task_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 8af5fbc60e5b..be1cf388c2ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -284,10 +284,16 @@ static void dce_v10_0_pageflip_interrupt_fini(struct amdgpu_device *adev)
  * surface base address.
  */
 static void dce_v10_0_page_flip(struct amdgpu_device *adev,
-			      int crtc_id, u64 crtc_base)
+				int crtc_id, u64 crtc_base, bool async)
 {
 	struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
+	u32 tmp;
 
+	/* flip at hsync for async, default is vsync */
+	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
+	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
+			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, async ? 1 : 0);
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
 	/* update the primary scanout address */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
@@ -2211,6 +2217,14 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 
 	dce_v10_0_vga_enable(crtc, false);
 
+	/* Make sure surface address is updated at vertical blank rather than
+	 * horizontal blank
+	 */
+	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
+	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
+			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, 0);
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
+
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(fb_location));
 	WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2261,13 +2275,6 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmVIEWPORT_SIZE + amdgpu_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
-	/* pageflip setup */
-	/* make sure flip is at vb rather than hb */
-	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
-	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
-			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, 0);
-	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
-
 	/* set pageflip to happen only at start of vblank interval (front porch) */
 	WREG32(mmMASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 3);
 
@@ -2992,6 +2999,8 @@ static int dce_v10_0_sw_init(void *handle)
 
 	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
 
+	adev->ddev->mode_config.async_page_flip = true;
+
 	adev->ddev->mode_config.max_width = 16384;
 	adev->ddev->mode_config.max_height = 16384;
 
@@ -3490,6 +3499,7 @@ static int dce_v10_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs dce_v10_0_ip_funcs = {
+	.name = "dce_v10_0",
 	.early_init = dce_v10_0_early_init,
 	.late_init = NULL,
 	.sw_init = dce_v10_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index dda9ffb68df8..1e0988572a2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -302,10 +302,17 @@ static void dce_v11_0_pageflip_interrupt_fini(struct amdgpu_device *adev)
  * surface base address.
  */
 static void dce_v11_0_page_flip(struct amdgpu_device *adev,
-			      int crtc_id, u64 crtc_base)
+				int crtc_id, u64 crtc_base, bool async)
 {
 	struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
+	u32 tmp;
 
+	/* flip at hsync for async, default is vsync */
+	/* use UPDATE_IMMEDIATE_EN instead for async? */
+	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
+	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
+			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, async ? 1 : 0);
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
 	/* update the scanout addresses */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
@@ -1595,6 +1602,7 @@ static const u32 pin_offsets[] =
 	AUD4_REGISTER_OFFSET,
 	AUD5_REGISTER_OFFSET,
 	AUD6_REGISTER_OFFSET,
+	AUD7_REGISTER_OFFSET,
 };
 
 static int dce_v11_0_audio_init(struct amdgpu_device *adev)
@@ -2185,6 +2193,14 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 
 	dce_v11_0_vga_enable(crtc, false);
 
+	/* Make sure surface address is updated at vertical blank rather than
+	 * horizontal blank
+	 */
+	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
+	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
+			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, 0);
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
+
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(fb_location));
 	WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2235,13 +2251,6 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmVIEWPORT_SIZE + amdgpu_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
-	/* pageflip setup */
-	/* make sure flip is at vb rather than hb */
-	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
-	tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL,
-			    GRPH_SURFACE_UPDATE_H_RETRACE_EN, 0);
-	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
-
 	/* set pageflip to happen only at start of vblank interval (front porch) */
 	WREG32(mmCRTC_MASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 3);
 
@@ -2419,10 +2428,6 @@ static u32 dce_v11_0_pick_pll(struct drm_crtc *crtc)
 
 		if (ENCODER_MODE_IS_DP(amdgpu_atombios_encoder_get_encoder_mode(amdgpu_crtc->encoder)))
 			return ATOM_DP_DTO;
-		/* use the same PPLL for all monitors with the same clock */
-		pll = amdgpu_pll_get_shared_nondp_ppll(crtc);
-		if (pll != ATOM_PPLL_INVALID)
-			return pll;
 
 		switch (amdgpu_encoder->encoder_id) {
 		case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
@@ -3046,6 +3051,8 @@ static int dce_v11_0_sw_init(void *handle)
 
 	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
 
+	adev->ddev->mode_config.async_page_flip = true;
+
 	adev->ddev->mode_config.max_width = 16384;
 	adev->ddev->mode_config.max_height = 16384;
 
@@ -3553,6 +3560,7 @@ static int dce_v11_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs dce_v11_0_ip_funcs = {
+	.name = "dce_v11_0",
 	.early_init = dce_v11_0_early_init,
 	.late_init = NULL,
 	.sw_init = dce_v11_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 25e6af03c406..c087f930d67e 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -233,10 +233,13 @@ static void dce_v8_0_pageflip_interrupt_fini(struct amdgpu_device *adev)
  * surface base address.
  */
 static void dce_v8_0_page_flip(struct amdgpu_device *adev,
-			      int crtc_id, u64 crtc_base)
+			       int crtc_id, u64 crtc_base, bool async)
 {
 	struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id];
 
+	/* flip at hsync for async, default is vsync */
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, async ?
+	       GRPH_FLIP_CONTROL__GRPH_SURFACE_UPDATE_H_RETRACE_EN_MASK : 0);
 	/* update the primary scanout addresses */
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(crtc_base));
@@ -1999,7 +2002,7 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	uint32_t fb_format, fb_pitch_pixels;
 	u32 fb_swap = (GRPH_ENDIAN_NONE << GRPH_SWAP_CNTL__GRPH_ENDIAN_SWAP__SHIFT);
 	u32 pipe_config;
-	u32 tmp, viewport_w, viewport_h;
+	u32 viewport_w, viewport_h;
 	int r;
 	bool bypass_lut = false;
 
@@ -2135,6 +2138,11 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 
 	dce_v8_0_vga_enable(crtc, false);
 
+	/* Make sure surface address is updated at vertical blank rather than
+	 * horizontal blank
+	 */
+	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, 0);
+
 	WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
 	       upper_32_bits(fb_location));
 	WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset,
@@ -2182,12 +2190,6 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(mmVIEWPORT_SIZE + amdgpu_crtc->crtc_offset,
 	       (viewport_w << 16) | viewport_h);
 
-	/* pageflip setup */
-	/* make sure flip is at vb rather than hb */
-	tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset);
-	tmp &= ~GRPH_FLIP_CONTROL__GRPH_SURFACE_UPDATE_H_RETRACE_EN_MASK;
-	WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp);
-
 	/* set pageflip to happen only at start of vblank interval (front porch) */
 	WREG32(mmMASTER_UPDATE_MODE + amdgpu_crtc->crtc_offset, 3);
 
@@ -2902,6 +2904,8 @@ static int dce_v8_0_sw_init(void *handle)
 
 	adev->ddev->mode_config.funcs = &amdgpu_mode_funcs;
 
+	adev->ddev->mode_config.async_page_flip = true;
+
 	adev->ddev->mode_config.max_width = 16384;
 	adev->ddev->mode_config.max_height = 16384;
 
@@ -3420,6 +3424,7 @@ static int dce_v8_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs dce_v8_0_ip_funcs = {
+	.name = "dce_v8_0",
 	.early_init = dce_v8_0_early_init,
 	.late_init = NULL,
 	.sw_init = dce_v8_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
index 6d133450d3cc..245cabf06575 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
@@ -143,6 +143,7 @@ static int fiji_dpm_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs fiji_dpm_ip_funcs = {
+	.name = "fiji_dpm",
 	.early_init = fiji_dpm_early_init,
 	.late_init = NULL,
 	.sw_init = fiji_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 6686c9c3005d..7f18a53ab53a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -53,7 +53,6 @@
 static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
-int gfx_v7_0_get_cu_info(struct amdgpu_device *, struct amdgpu_cu_info *);
 
 MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
 MODULE_FIRMWARE("radeon/bonaire_me.bin");
@@ -882,6 +881,7 @@ static u32 gfx_v7_0_get_csb_size(struct amdgpu_device *adev);
 static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer);
 static void gfx_v7_0_init_cp_pg_table(struct amdgpu_device *adev);
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev);
+static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev);
 
 /*
  * Core functions
@@ -1718,6 +1718,7 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev)
 	gfx_v7_0_tiling_mode_table_init(adev);
 
 	gfx_v7_0_setup_rb(adev);
+	gfx_v7_0_get_cu_info(adev);
 
 	/* set HW defaults for 3D engine */
 	WREG32(mmCP_MEQ_THRESHOLDS,
@@ -2029,17 +2030,13 @@ static void gfx_v7_0_ring_emit_fence_compute(struct amdgpu_ring *ring,
  * on the gfx ring for execution by the GPU.
  */
 static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+				      struct amdgpu_ib *ib,
+				      unsigned vm_id, bool ctx_switch)
 {
-	bool need_ctx_switch = ring->current_ctx != ib->ctx;
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
 
-	/* drop the CE preamble IB for the same context */
-	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
-		return;
-
-	if (need_ctx_switch)
+	if (ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -2050,7 +2047,7 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch) {
+	if (ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -2060,7 +2057,7 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (ib->vm_id << 24);
+	control |= ib->length_dw | (vm_id << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -2073,7 +2070,8 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 }
 
 static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+					  struct amdgpu_ib *ib,
+					  unsigned vm_id, bool ctx_switch)
 {
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
@@ -2088,7 +2086,7 @@ static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 
 	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (ib->vm_id << 24);
+	control |= ib->length_dw | (vm_id << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -2136,7 +2134,7 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring)
 	ib.ptr[2] = 0xDEADBEEF;
 	ib.length_dw = 3;
 
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r)
 		goto err2;
 
@@ -3053,6 +3051,19 @@ static int gfx_v7_0_cp_resume(struct amdgpu_device *adev)
 static void gfx_v7_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	uint32_t seq = ring->fence_drv.sync_seq;
+	uint64_t addr = ring->fence_drv.gpu_addr;
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
+				 WAIT_REG_MEM_FUNCTION(3) | /* equal */
+				 WAIT_REG_MEM_ENGINE(usepfp)));   /* pfp or me */
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	amdgpu_ring_write(ring, seq);
+	amdgpu_ring_write(ring, 0xffffffff);
+	amdgpu_ring_write(ring, 4); /* poll interval */
+
 	if (usepfp) {
 		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
@@ -3080,18 +3091,6 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned vm_id, uint64_t pd_addr)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
-	uint32_t seq = ring->fence_drv.sync_seq;
-	uint64_t addr = ring->fence_drv.gpu_addr;
-
-	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
-	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-				 WAIT_REG_MEM_FUNCTION(3) | /* equal */
-				 WAIT_REG_MEM_ENGINE(usepfp)));   /* pfp or me */
-	amdgpu_ring_write(ring, addr & 0xfffffffc);
-	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
-	amdgpu_ring_write(ring, seq);
-	amdgpu_ring_write(ring, 0xffffffff);
-	amdgpu_ring_write(ring, 4); /* poll interval */
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
@@ -3869,18 +3868,13 @@ static u32 gfx_v7_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 
 static void gfx_v7_0_init_ao_cu_mask(struct amdgpu_device *adev)
 {
-	uint32_t tmp, active_cu_number;
-	struct amdgpu_cu_info cu_info;
-
-	gfx_v7_0_get_cu_info(adev, &cu_info);
-	tmp = cu_info.ao_cu_mask;
-	active_cu_number = cu_info.number;
+	u32 tmp;
 
-	WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, tmp);
+	WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask);
 
 	tmp = RREG32(mmRLC_MAX_PG_CU);
 	tmp &= ~RLC_MAX_PG_CU__MAX_POWERED_UP_CU_MASK;
-	tmp |= (active_cu_number << RLC_MAX_PG_CU__MAX_POWERED_UP_CU__SHIFT);
+	tmp |= (adev->gfx.cu_info.number << RLC_MAX_PG_CU__MAX_POWERED_UP_CU__SHIFT);
 	WREG32(mmRLC_MAX_PG_CU, tmp);
 }
 
@@ -4898,6 +4892,7 @@ static int gfx_v7_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs gfx_v7_0_ip_funcs = {
+	.name = "gfx_v7_0",
 	.early_init = gfx_v7_0_early_init,
 	.late_init = gfx_v7_0_late_init,
 	.sw_init = gfx_v7_0_sw_init,
@@ -5015,14 +5010,11 @@ static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev)
 }
 
 
-int gfx_v7_0_get_cu_info(struct amdgpu_device *adev,
-			 struct amdgpu_cu_info *cu_info)
+static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev)
 {
 	int i, j, k, counter, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
-
-	if (!adev || !cu_info)
-		return -EINVAL;
+	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
@@ -5053,6 +5045,4 @@ int gfx_v7_0_get_cu_info(struct amdgpu_device *adev,
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
-
-	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
index c04bfbabfc88..e747aa935c88 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h
@@ -32,6 +32,5 @@ void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev);
 void gfx_v7_0_rlc_stop(struct amdgpu_device *adev);
 uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-int gfx_v7_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 021c17e50d51..92647fbf5b8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -603,7 +603,7 @@ static const u32 stoney_golden_settings_a11[] =
 	mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
 	mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c,
 	mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
-  	mmTCC_CTRL, 0x00100000, 0xf31fff7f,
+	mmTCC_CTRL, 0x00100000, 0xf31fff7f,
 	mmTCC_EXE_DISABLE, 0x00000002, 0x00000002,
 	mmTCP_ADDR_CONFIG, 0x0000000f, 0x000000f1,
 	mmTCP_CHAN_STEER_LO, 0xffffffff, 0x10101010,
@@ -636,6 +636,7 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev);
 static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev);
 static u32 gfx_v8_0_get_csb_size(struct amdgpu_device *adev);
+static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev);
 
 static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev)
 {
@@ -800,7 +801,7 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring)
 	ib.ptr[2] = 0xDEADBEEF;
 	ib.length_dw = 3;
 
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r)
 		goto err2;
 
@@ -1551,7 +1552,7 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 	ib.ptr[ib.length_dw++] = EVENT_TYPE(7) | EVENT_INDEX(4);
 
 	/* shedule the ib on the ring */
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r) {
 		DRM_ERROR("amdgpu: ib submit failed (%d).\n", r);
 		goto fail;
@@ -3431,6 +3432,7 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev)
 	gfx_v8_0_tiling_mode_table_init(adev);
 
 	gfx_v8_0_setup_rb(adev);
+	gfx_v8_0_get_cu_info(adev);
 
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
@@ -5644,17 +5646,13 @@ static void gfx_v8_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
 }
 
 static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+				      struct amdgpu_ib *ib,
+				      unsigned vm_id, bool ctx_switch)
 {
-	bool need_ctx_switch = ring->current_ctx != ib->ctx;
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
 
-	/* drop the CE preamble IB for the same context */
-	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
-		return;
-
-	if (need_ctx_switch)
+	if (ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -5665,7 +5663,7 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch) {
+	if (ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -5675,7 +5673,7 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (ib->vm_id << 24);
+	control |= ib->length_dw | (vm_id << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -5688,7 +5686,8 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 }
 
 static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+					  struct amdgpu_ib *ib,
+					  unsigned vm_id, bool ctx_switch)
 {
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
@@ -5704,7 +5703,7 @@ static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
 
 	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
-	control |= ib->length_dw | (ib->vm_id << 24);
+	control |= ib->length_dw | (vm_id << 24);
 
 	amdgpu_ring_write(ring, header);
 	amdgpu_ring_write(ring,
@@ -6064,6 +6063,7 @@ static int gfx_v8_0_priv_inst_irq(struct amdgpu_device *adev,
 }
 
 const struct amd_ip_funcs gfx_v8_0_ip_funcs = {
+	.name = "gfx_v8_0",
 	.early_init = gfx_v8_0_early_init,
 	.late_init = gfx_v8_0_late_init,
 	.sw_init = gfx_v8_0_sw_init,
@@ -6212,14 +6212,11 @@ static u32 gfx_v8_0_get_cu_active_bitmap(struct amdgpu_device *adev)
 	return (~data) & mask;
 }
 
-int gfx_v8_0_get_cu_info(struct amdgpu_device *adev,
-			 struct amdgpu_cu_info *cu_info)
+static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev)
 {
 	int i, j, k, counter, active_cu_number = 0;
 	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
-
-	if (!adev || !cu_info)
-		return -EINVAL;
+	struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info;
 
 	memset(cu_info, 0, sizeof(*cu_info));
 
@@ -6250,6 +6247,4 @@ int gfx_v8_0_get_cu_info(struct amdgpu_device *adev,
 
 	cu_info->number = active_cu_number;
 	cu_info->ao_cu_mask = ao_cu_mask;
-
-	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
index 021e05193cb9..16a49f53a2fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h
@@ -28,6 +28,5 @@ extern const struct amd_ip_funcs gfx_v8_0_ip_funcs;
 
 uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev);
 void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num);
-int gfx_v8_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 48e4800eafcc..1feb6439cb0b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1261,6 +1261,7 @@ static int gmc_v7_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs gmc_v7_0_ip_funcs = {
+	.name = "gmc_v7_0",
 	.early_init = gmc_v7_0_early_init,
 	.late_init = gmc_v7_0_late_init,
 	.sw_init = gmc_v7_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 53c3339e2cfd..9945d5bbf1fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1423,6 +1423,7 @@ static int gmc_v8_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs gmc_v8_0_ip_funcs = {
+	.name = "gmc_v8_0",
 	.early_init = gmc_v8_0_early_init,
 	.late_init = gmc_v8_0_late_init,
 	.sw_init = gmc_v8_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
index 57a96132a8a2..460bc8ad37e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
@@ -157,6 +157,7 @@ static int iceland_dpm_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs iceland_dpm_ip_funcs = {
+	.name = "iceland_dpm",
 	.early_init = iceland_dpm_early_init,
 	.late_init = NULL,
 	.sw_init = iceland_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index 5c4001e2538e..39bfc52d0b42 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -394,6 +394,7 @@ static int iceland_ih_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs iceland_ih_ip_funcs = {
+	.name = "iceland_ih",
 	.early_init = iceland_ih_early_init,
 	.late_init = NULL,
 	.sw_init = iceland_ih_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 4bd1e551cccd..b45f54714574 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -135,11 +135,6 @@ static void sumo_take_smu_control(struct amdgpu_device *adev, bool enable)
 #endif
 }
 
-static u32 sumo_get_sleep_divider_from_id(u32 id)
-{
-	return 1 << id;
-}
-
 static void sumo_construct_sclk_voltage_mapping_table(struct amdgpu_device *adev,
 						      struct sumo_sclk_voltage_mapping_table *sclk_voltage_mapping_table,
 						      ATOM_AVAILABLE_SCLK_LIST *table)
@@ -2176,8 +2171,7 @@ static u8 kv_get_sleep_divider_id_from_clock(struct amdgpu_device *adev,
 	struct kv_power_info *pi = kv_get_pi(adev);
 	u32 i;
 	u32 temp;
-	u32 min = (min_sclk_in_sr > KV_MINIMUM_ENGINE_CLOCK) ?
-		min_sclk_in_sr : KV_MINIMUM_ENGINE_CLOCK;
+	u32 min = max(min_sclk_in_sr, (u32)KV_MINIMUM_ENGINE_CLOCK);
 
 	if (sclk < min)
 		return 0;
@@ -2186,7 +2180,7 @@ static u8 kv_get_sleep_divider_id_from_clock(struct amdgpu_device *adev,
 		return 0;
 
 	for (i = KV_MAX_DEEPSLEEP_DIVIDER_ID; i > 0; i--) {
-		temp = sclk / sumo_get_sleep_divider_from_id(i);
+		temp = sclk >> i;
 		if (temp >= min)
 			break;
 	}
@@ -3244,6 +3238,7 @@ static int kv_dpm_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs kv_dpm_ip_funcs = {
+	.name = "kv_dpm",
 	.early_init = kv_dpm_early_init,
 	.late_init = kv_dpm_late_init,
 	.sw_init = kv_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index e6d3544fda06..f4c3130d3fdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -242,9 +242,10 @@ static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  * Schedule an IB in the DMA ring (VI).
  */
 static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
-				   struct amdgpu_ib *ib)
+				   struct amdgpu_ib *ib,
+				   unsigned vm_id, bool ctx_switch)
 {
-	u32 vmid = ib->vm_id & 0xf;
+	u32 vmid = vm_id & 0xf;
 	u32 next_rptr = ring->wptr + 5;
 
 	while ((next_rptr & 7) != 2)
@@ -701,7 +702,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring)
 	ib.ptr[7] = SDMA_PKT_HEADER_OP(SDMA_OP_NOP);
 	ib.length_dw = 8;
 
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r)
 		goto err1;
 
@@ -1230,6 +1231,7 @@ static int sdma_v2_4_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs sdma_v2_4_ip_funcs = {
+	.name = "sdma_v2_4",
 	.early_init = sdma_v2_4_early_init,
 	.late_init = NULL,
 	.sw_init = sdma_v2_4_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 00b43700c956..063f08a9957a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -400,9 +400,10 @@ static void sdma_v3_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
  * Schedule an IB in the DMA ring (VI).
  */
 static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
-				   struct amdgpu_ib *ib)
+				   struct amdgpu_ib *ib,
+				   unsigned vm_id, bool ctx_switch)
 {
-	u32 vmid = ib->vm_id & 0xf;
+	u32 vmid = vm_id & 0xf;
 	u32 next_rptr = ring->wptr + 5;
 
 	while ((next_rptr & 7) != 2)
@@ -925,7 +926,7 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring)
 	ib.ptr[7] = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP);
 	ib.length_dw = 8;
 
-	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
+	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, NULL, &f);
 	if (r)
 		goto err1;
 
@@ -1542,6 +1543,7 @@ static int sdma_v3_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs sdma_v3_0_ip_funcs = {
+	.name = "sdma_v3_0",
 	.early_init = sdma_v3_0_early_init,
 	.late_init = NULL,
 	.sw_init = sdma_v3_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
index 552f0f42a39f..b7615cefcac4 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
@@ -143,6 +143,7 @@ static int tonga_dpm_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs tonga_dpm_ip_funcs = {
+	.name = "tonga_dpm",
 	.early_init = tonga_dpm_early_init,
 	.late_init = NULL,
 	.sw_init = tonga_dpm_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index 55cdab849089..f036af937fbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -417,6 +417,7 @@ static int tonga_ih_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs tonga_ih_ip_funcs = {
+	.name = "tonga_ih",
 	.early_init = tonga_ih_early_init,
 	.late_init = NULL,
 	.sw_init = tonga_ih_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index abd37a7eb4c6..f07551476a70 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -489,7 +489,8 @@ static int uvd_v4_2_ring_test_ring(struct amdgpu_ring *ring)
  * Write ring commands to execute the indirect buffer
  */
 static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+				  struct amdgpu_ib *ib,
+				  unsigned vm_id, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_RBC_IB_BASE, 0));
 	amdgpu_ring_write(ring, ib->gpu_addr);
@@ -739,6 +740,7 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs uvd_v4_2_ip_funcs = {
+	.name = "uvd_v4_2",
 	.early_init = uvd_v4_2_early_init,
 	.late_init = NULL,
 	.sw_init = uvd_v4_2_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 1c1a0e2c7e0f..e0a76a883d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -539,7 +539,8 @@ static int uvd_v5_0_ring_test_ring(struct amdgpu_ring *ring)
  * Write ring commands to execute the indirect buffer
  */
 static void uvd_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+				  struct amdgpu_ib *ib,
+				  unsigned vm_id, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
@@ -791,6 +792,7 @@ static int uvd_v5_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs uvd_v5_0_ip_funcs = {
+	.name = "uvd_v5_0",
 	.early_init = uvd_v5_0_early_init,
 	.late_init = NULL,
 	.sw_init = uvd_v5_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index d015cb0c9eb5..c9929d665c01 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -631,7 +631,8 @@ static int uvd_v6_0_ring_test_ring(struct amdgpu_ring *ring)
  * Write ring commands to execute the indirect buffer
  */
 static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
-				  struct amdgpu_ib *ib)
+				  struct amdgpu_ib *ib,
+				  unsigned vm_id, bool ctx_switch)
 {
 	amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0));
 	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
@@ -895,6 +896,7 @@ static int uvd_v6_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs uvd_v6_0_ip_funcs = {
+	.name = "uvd_v6_0",
 	.early_init = uvd_v6_0_early_init,
 	.late_init = NULL,
 	.sw_init = uvd_v6_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 95f6e579427d..45d92aceb485 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -567,6 +567,7 @@ static int vce_v2_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs vce_v2_0_ip_funcs = {
+	.name = "vce_v2_0",
 	.early_init = vce_v2_0_early_init,
 	.late_init = NULL,
 	.sw_init = vce_v2_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index e1d6ae7e1629..30e8099e94c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -40,9 +40,9 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
-#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 	0x8616
-#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 	0x8617
-#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 	0x8618
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0	0x8616
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1	0x8617
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2	0x8618
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
@@ -674,6 +674,7 @@ static int vce_v3_0_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs vce_v3_0_ip_funcs = {
+	.name = "vce_v3_0",
 	.early_init = vce_v3_0_early_init,
 	.late_init = NULL,
 	.sw_init = vce_v3_0_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 340a166da911..2c88d0b66cf3 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1118,7 +1118,6 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_xclk = &vi_get_xclk,
 	.set_uvd_clocks = &vi_set_uvd_clocks,
 	.set_vce_clocks = &vi_set_vce_clocks,
-	.get_cu_info = &gfx_v8_0_get_cu_info,
 	/* these should be moved to their own ip modules */
 	.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
 	.wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle,
@@ -1193,7 +1192,8 @@ static int vi_common_early_init(void *handle)
 		adev->external_rev_id = adev->rev_id + 0x50;
 		break;
 	case CHIP_CARRIZO:
-		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
+		adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
 			AMD_CG_SUPPORT_GFX_RLC_LS |
 			AMD_CG_SUPPORT_GFX_CP_LS |
@@ -1408,6 +1408,7 @@ static int vi_common_set_powergating_state(void *handle,
 }
 
 const struct amd_ip_funcs vi_common_ip_funcs = {
+	.name = "vi_common",
 	.early_init = vi_common_early_init,
 	.late_init = NULL,
 	.sw_init = vi_common_sw_init,
diff --git a/drivers/gpu/drm/amd/amdgpu/vid.h b/drivers/gpu/drm/amd/amdgpu/vid.h
index ace49976f7be..062ee1676480 100644
--- a/drivers/gpu/drm/amd/amdgpu/vid.h
+++ b/drivers/gpu/drm/amd/amdgpu/vid.h
@@ -54,7 +54,8 @@
 #define AUD3_REGISTER_OFFSET                 (0x17b4 - 0x17a8)
 #define AUD4_REGISTER_OFFSET                 (0x17b8 - 0x17a8)
 #define AUD5_REGISTER_OFFSET                 (0x17bc - 0x17a8)
-#define AUD6_REGISTER_OFFSET                 (0x17c4 - 0x17a8)
+#define AUD6_REGISTER_OFFSET                 (0x17c0 - 0x17a8)
+#define AUD7_REGISTER_OFFSET                 (0x17c4 - 0x17a8)
 
 /* hpd instance offsets */
 #define HPD0_REGISTER_OFFSET                 (0x1898 - 0x1898)
@@ -365,7 +366,7 @@
 #define VCE_CMD_IB		0x00000002
 #define VCE_CMD_FENCE		0x00000003
 #define VCE_CMD_TRAP		0x00000004
-#define VCE_CMD_IB_AUTO 	0x00000005
+#define VCE_CMD_IB_AUTO	0x00000005
 #define VCE_CMD_SEMAPHORE	0x00000006
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index ea9ee4644139..6080951d539d 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -143,6 +143,8 @@ enum amd_pm_state_type {
 };
 
 struct amd_ip_funcs {
+	/* Name of IP block */
+	char *name;
 	/* sets up early driver state (pre sw_init), does not configure hw - Optional */
 	int (*early_init)(void *handle);
 	/* sets up late driver/hw state (post hw_init) - Optional */
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index aba587cfce81..8e345bfddb69 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -68,15 +68,18 @@ static int pp_sw_init(void *handle)
 		return -EINVAL;
 
 	ret = hwmgr->pptable_func->pptable_init(hwmgr);
+	if (ret)
+		goto err;
 
-	if (ret == 0)
-		ret = hwmgr->hwmgr_func->backend_init(hwmgr);
-
+	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
-		printk(KERN_ERR "amdgpu: powerplay initialization failed\n");
-	else
-		printk(KERN_INFO "amdgpu: powerplay initialized\n");
+		goto err;
 
+	pr_info("amdgpu: powerplay initialized\n");
+
+	return 0;
+err:
+	pr_err("amdgpu: powerplay initialization failed\n");
 	return ret;
 }
 
@@ -340,6 +343,7 @@ static int pp_resume(void *handle)
 }
 
 const struct amd_ip_funcs pp_ip_funcs = {
+	.name = "powerplay",
 	.early_init = pp_early_init,
 	.late_init = NULL,
 	.sw_init = pp_sw_init,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index 55e877c4b862..c94f9faa220a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -465,14 +465,14 @@ static int fiji_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
 			table_info->vdd_dep_on_mclk;
 
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table != NULL,
-		"VDD dependency on SCLK table is missing. 	\
+		"VDD dependency on SCLK table is missing.	\
 		This table is mandatory", return -EINVAL);
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table->count >= 1,
-		"VDD dependency on SCLK table has to have is missing. 	\
+		"VDD dependency on SCLK table has to have is missing.	\
 		This table is mandatory", return -EINVAL);
 
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table != NULL,
-		"VDD dependency on MCLK table is missing. 	\
+		"VDD dependency on MCLK table is missing.	\
 		This table is mandatory", return -EINVAL);
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table->count >= 1,
 		"VDD dependency on MCLK table has to have is missing.	 \
@@ -1898,16 +1898,16 @@ static int fiji_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static uint8_t fiji_get_sleep_divider_id_from_clock(struct pp_hwmgr *hwmgr,
-						uint32_t clock, uint32_t clock_insr)
+static uint8_t fiji_get_sleep_divider_id_from_clock(uint32_t clock,
+		uint32_t clock_insr)
 {
 	uint8_t i;
 	uint32_t temp;
-	uint32_t min = clock_insr > 2500 ? clock_insr : 2500;
+	uint32_t min = max(clock_insr, (uint32_t)FIJI_MINIMUM_ENGINE_CLOCK);
 
 	PP_ASSERT_WITH_CODE((clock >= min), "Engine clock can't satisfy stutter requirement!", return 0);
 	for (i = FIJI_MAX_DEEPSLEEP_DIVIDER_ID;  ; i--) {
-		temp = clock / (1UL << i);
+		temp = clock >> i;
 
 		if (temp >= min || i == 0)
 			break;
@@ -1961,7 +1961,7 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	data->display_timing.min_clock_in_sr = hwmgr->display_config.min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
-		level->DeepSleepDivId = fiji_get_sleep_divider_id_from_clock(hwmgr, clock,
+		level->DeepSleepDivId = fiji_get_sleep_divider_id_from_clock(clock,
 								hwmgr->display_config.min_core_set_clock_in_sr);
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
index 010199fb7126..93768fa1dcdc 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c
@@ -1175,11 +1175,11 @@ static int polaris10_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	if (phm_cap_enabled(hwmgr->platformDescriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
 		level->DeepSleepDivId = PhwFiji_GetSleepDividerIdFromClock(hwmgr, clock, minClocks.engineClockInSR);
 	*/
-	PP_ASSERT_WITH_CODE((clock >= 2500), "Engine clock can't satisfy stutter requirement!", return 0);
+	PP_ASSERT_WITH_CODE((clock >= POLARIS10_MINIMUM_ENGINE_CLOCK), "Engine clock can't satisfy stutter requirement!", return 0);
 	for (i = POLARIS10_MAX_DEEPSLEEP_DIVIDER_ID;  ; i--) {
-		temp = clock / (1UL << i);
+		temp = clock >> i;
 
-		if (temp >= 2500 || i == 0)
+		if (temp >= POLARIS10_MINIMUM_ENGINE_CLOCK || i == 0)
 			break;
 	}
 
@@ -2900,14 +2900,14 @@ static int polaris10_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
 						table_info->vdd_dep_on_mclk;
 
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table != NULL,
-		"VDD dependency on SCLK table is missing. 	\
+		"VDD dependency on SCLK table is missing.	\
 		This table is mandatory", return -EINVAL);
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table->count >= 1,
-		"VDD dependency on SCLK table has to have is missing. 	\
+		"VDD dependency on SCLK table has to have is missing.	\
 		This table is mandatory", return -EINVAL);
 
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table != NULL,
-		"VDD dependency on MCLK table is missing. 	\
+		"VDD dependency on MCLK table is missing.	\
 		This table is mandatory", return -EINVAL);
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table->count >= 1,
 		"VDD dependency on MCLK table has to have is missing.	 \
@@ -4628,7 +4628,7 @@ int polaris10_upload_mc_firmware(struct pp_hwmgr *hwmgr)
 	data->need_long_memory_training = true;
 
 /*
- * 	PPMCME_FirmwareDescriptorEntry *pfd = NULL;
+ *	PPMCME_FirmwareDescriptorEntry *pfd = NULL;
 	pfd = &tonga_mcmeFirmware;
 	if (0 == PHM_READ_FIELD(hwmgr->device, MC_SEQ_SUP_CNTL, RUN))
 		polaris10_load_mc_microcode(hwmgr, pfd->dpmThreshold,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
index 7b2d5000292d..58742e0d1492 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c
@@ -1,3 +1,26 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
 #include <linux/errno.h>
 #include "linux/delay.h"
 #include "hwmgr.h"
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 8ba3ad5e7111..da9f5f1b6dc2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1041,10 +1041,10 @@ int atomctrl_calculate_voltage_evv_on_sclk(
 }
 
 /** atomctrl_get_voltage_evv_on_sclk gets voltage via call to ATOM COMMAND table.
- * @param hwmgr               	input: pointer to hwManager
+ * @param hwmgr	input: pointer to hwManager
  * @param voltage_type            input: type of EVV voltage VDDC or VDDGFX
  * @param sclk                        input: in 10Khz unit. DPM state SCLK frequency
- *                                   		which is define in PPTable SCLK/VDDC dependence
+ *		which is define in PPTable SCLK/VDDC dependence
  *				table associated with this virtual_voltage_Id
  * @param virtual_voltage_Id      input: voltage id which match per voltage DPM state: 0xff01, 0xff02.. 0xff08
  * @param voltage		       output: real voltage level in unit of mv
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 670b6288933f..1faad92b50d3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -2416,18 +2416,17 @@ int tonga_calculate_sclk_params(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static uint8_t tonga_get_sleep_divider_id_from_clock(struct pp_hwmgr *hwmgr,
-		uint32_t engine_clock, uint32_t min_engine_clock_in_sr)
+static uint8_t tonga_get_sleep_divider_id_from_clock(uint32_t engine_clock,
+		uint32_t min_engine_clock_in_sr)
 {
 	uint32_t i, temp;
-	uint32_t min = (min_engine_clock_in_sr > TONGA_MINIMUM_ENGINE_CLOCK) ?
-			min_engine_clock_in_sr : TONGA_MINIMUM_ENGINE_CLOCK;
+	uint32_t min = max(min_engine_clock_in_sr, (uint32_t)TONGA_MINIMUM_ENGINE_CLOCK);
 
 	PP_ASSERT_WITH_CODE((engine_clock >= min),
 			"Engine clock can't satisfy stutter requirement!", return 0);
 
 	for (i = TONGA_MAX_DEEPSLEEP_DIVIDER_ID;; i--) {
-		temp = engine_clock / (1 << i);
+		temp = engine_clock >> i;
 
 		if(temp >= min || i == 0)
 			break;
@@ -2487,7 +2486,7 @@ static int tonga_populate_single_graphic_level(struct pp_hwmgr *hwmgr, uint32_t
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_SclkDeepSleep))
 		graphic_level->DeepSleepDivId =
-				tonga_get_sleep_divider_id_from_clock(hwmgr, engine_clock,
+				tonga_get_sleep_divider_id_from_clock(engine_clock,
 						data->display_timing.min_clock_insr);
 
 	/* Default to slow, highest DPM level will be set to PPSMC_DISPLAY_WATERMARK_LOW later.*/
@@ -2683,7 +2682,7 @@ static int tonga_populate_all_memory_levels(struct pp_hwmgr *hwmgr)
 struct TONGA_DLL_SPEED_SETTING {
 	uint16_t            Min;                          /* Minimum Data Rate*/
 	uint16_t            Max;                          /* Maximum Data Rate*/
-	uint32_t 			dll_speed;                     /* The desired DLL_SPEED setting*/
+	uint32_t			dll_speed;                     /* The desired DLL_SPEED setting*/
 };
 
 static int tonga_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
@@ -3316,14 +3315,14 @@ static int tonga_set_private_var_based_on_pptale(struct pp_hwmgr *hwmgr)
 		pptable_info->vdd_dep_on_mclk;
 
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table != NULL,
-		"VDD dependency on SCLK table is missing. 	\
+		"VDD dependency on SCLK table is missing.	\
 		This table is mandatory", return -1);
 	PP_ASSERT_WITH_CODE(allowed_sclk_vdd_table->count >= 1,
-		"VDD dependency on SCLK table has to have is missing. 	\
+		"VDD dependency on SCLK table has to have is missing.	\
 		This table is mandatory", return -1);
 
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table != NULL,
-		"VDD dependency on MCLK table is missing. 	\
+		"VDD dependency on MCLK table is missing.	\
 		This table is mandatory", return -1);
 	PP_ASSERT_WITH_CODE(allowed_mclk_vdd_table->count >= 1,
 		"VDD dependency on MCLK table has to have is missing.	 \
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
index c6a6b4006dc1..573cd39fe78d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h
@@ -74,7 +74,7 @@ struct tonga_power_state {
 };
 
 struct _phw_tonga_dpm_level {
-	bool  		enabled;
+	bool		enabled;
 	uint32_t    value;
 	uint32_t    param1;
 };
@@ -237,20 +237,20 @@ struct tonga_hwmgr {
 	irq_handler_func_t             ctf_callback;
 	void                             *ctf_context;
 
-	phw_tonga_clock_registers      	  clock_registers;
+	phw_tonga_clock_registers	  clock_registers;
 	phw_tonga_voltage_smio_registers  voltage_smio_registers;
 
-	bool                         	is_memory_GDDR5;
+	bool	is_memory_GDDR5;
 	uint16_t                          acpi_vddc;
-	bool                         	pspp_notify_required;        /* Flag to indicate if PSPP notification to SBIOS is required */
+	bool	pspp_notify_required;        /* Flag to indicate if PSPP notification to SBIOS is required */
 	uint16_t                          force_pcie_gen;            /* The forced PCI-E speed if not 0xffff */
 	uint16_t                          acpi_pcie_gen;             /* The PCI-E speed at ACPI time */
 	uint32_t                           pcie_gen_cap;             /* The PCI-E speed capabilities bitmap from CAIL */
 	uint32_t                           pcie_lane_cap;            /* The PCI-E lane capabilities bitmap from CAIL */
 	uint32_t                           pcie_spc_cap;             /* Symbol Per Clock Capabilities from registry */
-	phw_tonga_leakage_voltage       	vddc_leakage;            /* The Leakage VDDC supported (based on leakage ID).*/
-	phw_tonga_leakage_voltage       	vddcgfx_leakage;         /* The Leakage VDDC supported (based on leakage ID). */
-	phw_tonga_leakage_voltage       	vddci_leakage;           /* The Leakage VDDCI supported (based on leakage ID). */
+	phw_tonga_leakage_voltage	vddc_leakage;            /* The Leakage VDDC supported (based on leakage ID).*/
+	phw_tonga_leakage_voltage	vddcgfx_leakage;         /* The Leakage VDDC supported (based on leakage ID). */
+	phw_tonga_leakage_voltage	vddci_leakage;           /* The Leakage VDDCI supported (based on leakage ID). */
 
 	uint32_t                           mvdd_control;
 	uint32_t                           vddc_mask_low;
@@ -263,8 +263,8 @@ struct tonga_hwmgr {
 	uint32_t                           mclk_stutter_mode_threshold;
 	uint32_t                           mclk_edc_enable_threshold;
 	uint32_t                           mclk_edc_wr_enable_threshold;
-	bool                         	is_uvd_enabled;
-	bool                         	is_xdma_enabled;
+	bool	is_uvd_enabled;
+	bool	is_xdma_enabled;
 	phw_tonga_vbios_boot_state      vbios_boot_state;
 
 	bool                         battery_state;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index c96e5b1baae0..fd4ce7aaeee9 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -500,7 +500,7 @@ struct phm_dynamic_state_info {
 	struct phm_ppm_table                          *ppm_parameter_table;
 	struct phm_cac_tdp_table                      *cac_dtp_table;
 	struct phm_clock_voltage_dependency_table	  *vdd_gfx_dependency_on_sclk;
-	struct phm_vq_budgeting_table		  		  *vq_budgeting_table;
+	struct phm_vq_budgeting_table				  *vq_budgeting_table;
 };
 
 struct pp_fan_info {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h b/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h
index f8ba071f39c8..eb0f79f9c876 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_ucode_xfer_cz.h
@@ -1,3 +1,25 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
 // CZ Ucode Loading Definitions
 #ifndef SMU_UCODE_XFER_CZ_H
 #define SMU_UCODE_XFER_CZ_H
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 169f70fe949c..070095a9433c 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -74,7 +74,7 @@ struct amd_sched_fence {
 	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
-	struct amd_sched_job 	*s_job;
+	struct amd_sched_job	*s_job;
 };
 
 struct amd_sched_job {