[Intel-gfx] [PATCH] drm/i915: Remove OLR

Daniel Vetter daniel at ffwll.ch
Tue Jan 6 05:52:03 PST 2015


On Fri, Dec 19, 2014 at 02:41:05PM +0000, John.C.Harrison at Intel.com wrote:
> From: John Harrison <John.C.Harrison at Intel.com>
> 
> The outstanding lazy request mechanism does not really work well with
> a GPU scheduler. The scheduler expects each work packet, i.e. request
> structure, to be a complete entity and to belong to one and only one
> submitter. Whereas the whole lazy mechanism allows lots of work from
> lots of different places to all be lumped together into a single
> request. It also means that work is floating around in the system
> unowned and untracked at various random points in time. This all
> causes headaches for the scheduler.
> 
> This patch removes the need for the outstanding lazy request. It
> converts all functions which would otherwise be relying on the OLR to
> explicitly manage the request. Either by allocating, passing and
> submitting the request if they are the top level owner. Or by simply
> taking a request in as a parameter rather than pulling it out of the
> magic global variable if they are a client. The OLR itself is left in
> along with a bunch of sanity check asserts that it matches the request
> being passed in as a parameter. However, it should now be safe to
> remove completely.
> 
> Note that this patch is not intended as a final, shipping, isn't it
> gorgeous, end product. It is merely a quick hack that I went through
> as being the simplest way to actually work out what the real sequence
> of events and the real ownership of work is in certain circumstances.
> Most particularly to do with display and overlay work. However, I
> would like to get agreement that it is a good direction to go in and
> that removing the OLR would be a good thing. Or, to put it another
> way, is it worth me trying to break this patch into a set of
> manageable items or do I just abandon it and give up?
> 
> Note also that the patch is based on a tree including the scheduler
> prep-work patches posted earlier. So it will not apply to a clean
> nightly tree.
> 
> Signed-off-by: John Harrison <John.C.Harrison at Intel.com>

Summarizing offline discussions from a meeting about John's rfc here:

I definitely like where this is going, using requests as the primary
object to submit work to the gpu should simplify our code a lot. And
getting rid of the olr will remove a lot of the accidental complexity in
gem. I also looked at some of the details here with John specifically that
he chuffles the init_hw functions around a bit to just have 1 request to
wrap all the ring init (default ctx, ppgtt, l3 remapping).

For the details it'd be good to discuss this all with Chris since he's got
a working poc for this, just to make sure you know about all the dragons
potentially lurking around.
-Daniel

> ---
>  drivers/gpu/drm/i915/i915_drv.h              |   29 ++--
>  drivers/gpu/drm/i915/i915_gem.c              |  182 ++++++++++++--------
>  drivers/gpu/drm/i915/i915_gem_context.c      |   69 +++-----
>  drivers/gpu/drm/i915/i915_gem_execbuffer.c   |   62 +++----
>  drivers/gpu/drm/i915/i915_gem_gtt.c          |   64 ++++----
>  drivers/gpu/drm/i915/i915_gem_gtt.h          |    3 +-
>  drivers/gpu/drm/i915/i915_gem_render_state.c |   10 +-
>  drivers/gpu/drm/i915/i915_gem_render_state.h |    2 +-
>  drivers/gpu/drm/i915/intel_display.c         |   68 ++++----
>  drivers/gpu/drm/i915/intel_lrc.c             |  145 +++++++++-------
>  drivers/gpu/drm/i915/intel_lrc.h             |    8 +-
>  drivers/gpu/drm/i915/intel_overlay.c         |   58 ++++---
>  drivers/gpu/drm/i915/intel_pm.c              |   33 ++--
>  drivers/gpu/drm/i915/intel_ringbuffer.c      |  228 ++++++++++++++------------
>  drivers/gpu/drm/i915/intel_ringbuffer.h      |   38 ++---
>  15 files changed, 553 insertions(+), 446 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 511f55f..7b4309e 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -513,7 +513,7 @@ struct drm_i915_display_funcs {
>  	int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
>  			  struct drm_framebuffer *fb,
>  			  struct drm_i915_gem_object *obj,
> -			  struct intel_engine_cs *ring,
> +			  struct drm_i915_gem_request *req,
>  			  uint32_t flags);
>  	void (*update_primary_plane)(struct drm_crtc *crtc,
>  				     struct drm_framebuffer *fb,
> @@ -1796,7 +1796,8 @@ struct drm_i915_private {
>  	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
>  	struct {
>  		int (*alloc_request)(struct intel_engine_cs *ring,
> -				     struct intel_context *ctx);
> +				     struct intel_context *ctx,
> +				     struct drm_i915_gem_request **req_out);
>  		int (*do_execbuf)(struct i915_execbuffer_params *params,
>  				  struct drm_i915_gem_execbuffer2 *args,
>  				  struct list_head *vmas);
> @@ -2511,10 +2512,10 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
>  int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
>  			     struct drm_file *file_priv);
>  void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> -					struct intel_engine_cs *ring);
> +					struct drm_i915_gem_request *req);
>  void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
>  					 struct drm_file *file,
> -					 struct intel_engine_cs *ring,
> +					 struct drm_i915_gem_request *req,
>  					 struct drm_i915_gem_object *obj);
>  void i915_gem_execbuff_release_batch_obj(struct drm_i915_gem_object *batch_obj);
>  int i915_gem_ringbuffer_submission(struct i915_execbuffer_params *qe,
> @@ -2609,9 +2610,9 @@ int __must_check __i915_mutex_lock_interruptible(struct drm_device *dev, const c
>  int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
>  #endif
>  int i915_gem_object_sync(struct drm_i915_gem_object *obj,
> -			 struct intel_engine_cs *to, bool add_request);
> +			 struct drm_i915_gem_request *to_req);
>  void i915_vma_move_to_active(struct i915_vma *vma,
> -			     struct intel_engine_cs *ring);
> +			     struct drm_i915_gem_request *req);
>  int i915_gem_dumb_create(struct drm_file *file_priv,
>  			 struct drm_device *dev,
>  			 struct drm_mode_create_dumb *args);
> @@ -2678,19 +2679,19 @@ int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
>  int __must_check i915_gem_init(struct drm_device *dev);
>  int i915_gem_init_rings(struct drm_device *dev);
>  int __must_check i915_gem_init_hw(struct drm_device *dev);
> -int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
> +int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
>  void i915_gem_init_swizzling(struct drm_device *dev);
>  void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
>  int __must_check i915_gpu_idle(struct drm_device *dev);
>  int __must_check i915_gem_suspend(struct drm_device *dev);
> -int __i915_add_request(struct intel_engine_cs *ring,
> +int __i915_add_request(struct drm_i915_gem_request *req,
>  		       struct drm_file *file,
>  		       struct drm_i915_gem_object *batch_obj,
>  		       bool flush_caches);
> -#define i915_add_request(ring) \
> -	__i915_add_request(ring, NULL, NULL, true)
> -#define i915_add_request_no_flush(ring) \
> -	__i915_add_request(ring, NULL, NULL, false)
> +#define i915_add_request(req) \
> +	__i915_add_request(req, NULL, NULL, true)
> +#define i915_add_request_no_flush(req) \
> +	__i915_add_request(req, NULL, NULL, false)
>  int __i915_wait_request(struct drm_i915_gem_request *req,
>  			unsigned reset_counter,
>  			bool interruptible,
> @@ -2810,9 +2811,9 @@ int __must_check i915_gem_context_init(struct drm_device *dev);
>  void i915_gem_context_fini(struct drm_device *dev);
>  void i915_gem_context_reset(struct drm_device *dev);
>  int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
> -int i915_gem_context_enable(struct drm_i915_private *dev_priv);
> +int i915_gem_context_enable(struct drm_i915_gem_request *req);
>  void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
> -int i915_switch_context(struct intel_engine_cs *ring,
> +int i915_switch_context(struct drm_i915_gem_request *req,
>  			struct intel_context *to);
>  struct intel_context *
>  i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 1d2cbfb..dbfb4e5 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -1178,7 +1178,7 @@ i915_gem_check_olr(struct drm_i915_gem_request *req)
>  
>  	ret = 0;
>  	if (req == req->ring->outstanding_lazy_request)
> -		ret = i915_add_request(req->ring);
> +		ret = i915_add_request(req);
>  
>  	return ret;
>  }
> @@ -2294,17 +2294,16 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
>  
>  static void
>  i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
> -			       struct intel_engine_cs *ring)
> +			       struct drm_i915_gem_request *req)
>  {
> -	struct drm_i915_gem_request *req;
> -	struct intel_engine_cs *old_ring;
> +	struct intel_engine_cs *new_ring, *old_ring;
>  
> -	BUG_ON(ring == NULL);
> +	BUG_ON(req == NULL);
>  
> -	req = intel_ring_get_request(ring);
> +	new_ring = i915_gem_request_get_ring(req);
>  	old_ring = i915_gem_request_get_ring(obj->last_read_req);
>  
> -	if (old_ring != ring && obj->last_write_req) {
> +	if (old_ring != new_ring && obj->last_write_req) {
>  		/* Keep the request relative to the current ring */
>  		i915_gem_request_assign(&obj->last_write_req, req);
>  	}
> @@ -2315,17 +2314,17 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
>  		obj->active = 1;
>  	}
>  
> -	list_move_tail(&obj->ring_list, &ring->active_list);
> +	list_move_tail(&obj->ring_list, &new_ring->active_list);
>  
> -	//printk(KERN_INFO "%s:%d> <%s> obj = %p, last_read_req <= 0x%p\n", __func__, __LINE__, ring->name, obj, req);
> +	//printk(KERN_INFO "%s:%d> <%s> obj = %p, last_read_req <= 0x%p\n", __func__, __LINE__, new_ring->name, obj, req);
>  	i915_gem_request_assign(&obj->last_read_req, req);
>  }
>  
>  void i915_vma_move_to_active(struct i915_vma *vma,
> -			     struct intel_engine_cs *ring)
> +			     struct drm_i915_gem_request *req)
>  {
>  	list_move_tail(&vma->mm_list, &vma->vm->active_list);
> -	return i915_gem_object_move_to_active(vma->obj, ring);
> +	return i915_gem_object_move_to_active(vma->obj, req);
>  }
>  
>  static void
> @@ -2440,26 +2439,35 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
>  	return 0;
>  }
>  
> -int __i915_add_request(struct intel_engine_cs *ring,
> +int __i915_add_request(struct drm_i915_gem_request *request,
>  		       struct drm_file *file,
>  		       struct drm_i915_gem_object *obj,
>  		       bool flush_caches)
>  {
> -	struct drm_i915_private *dev_priv = ring->dev->dev_private;
> -	struct drm_i915_gem_request *request;
> +	struct intel_engine_cs *ring;
> +	struct drm_i915_private *dev_priv;
>  	struct intel_ringbuffer *ringbuf;
>  	u32 request_ring_position, request_start;
>  	int ret;
>  
> -	request = ring->outstanding_lazy_request;
> +	/*printk( KERN_ERR "<%s> request %c %d:%d, OLR %c %d:%d\n",
> +		request ? request->ring->name : "???",
> +		request ? '=' : '?',
> +		request ? request->uniq : -1,
> +		request ? request->seqno : 0,
> +		request->ring->outstanding_lazy_request ? '=' : '?',
> +		request->ring->outstanding_lazy_request ? request->ring->outstanding_lazy_request->uniq : -1,
> +		request->ring->outstanding_lazy_request ? request->ring->outstanding_lazy_request->seqno : 0);*/
> +	//dump_stack();
> +
>  	if (WARN_ON(request == NULL))
>  		return -ENOMEM;
>  
> -	if (i915.enable_execlists) {
> -		struct intel_context *ctx = request->ctx;
> -		ringbuf = ctx->engine[ring->id].ringbuf;
> -	} else
> -		ringbuf = ring->buffer;
> +	ring = request->ring;
> +	dev_priv = ring->dev->dev_private;
> +	ringbuf = request->ringbuf;
> +
> +	WARN_ON(request != ring->outstanding_lazy_request);
>  
>  	request_start = intel_ring_get_tail(ringbuf);
>  	/*
> @@ -2471,9 +2479,9 @@ int __i915_add_request(struct intel_engine_cs *ring,
>  	 */
>  	if (flush_caches) {
>  		if (i915.enable_execlists)
> -			ret = logical_ring_flush_all_caches(ringbuf);
> +			ret = logical_ring_flush_all_caches(request);
>  		else
> -			ret = intel_ring_flush_all_caches(ring);
> +			ret = intel_ring_flush_all_caches(request);
>  		if (ret)
>  			return ret;
>  	}
> @@ -2488,9 +2496,9 @@ int __i915_add_request(struct intel_engine_cs *ring,
>  	request_ring_position = intel_ring_get_tail(ringbuf);
>  
>  	if (i915.enable_execlists)
> -		ret = ring->emit_request(ringbuf);
> +		ret = ring->emit_request(request);
>  	else
> -		ret = ring->add_request(ring);
> +		ret = ring->add_request(request);
>  	if (ret)
>  		return ret;
>  
> @@ -2504,7 +2512,8 @@ int __i915_add_request(struct intel_engine_cs *ring,
>  	 * inactive_list and lose its active reference. Hence we do not need
>  	 * to explicitly hold another reference here.
>  	 */
> -	request->batch_obj = obj;
> +	if (obj)
> +		request->batch_obj = obj;
>  
>  	if (!i915.enable_execlists) {
>  		/* Hold a reference to the current context so that we can inspect
> @@ -2744,6 +2753,7 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
>  #endif
>  
>  	/* This may not have been flushed before the reset, so clean it now */
> +	WARN_ON(ring->outstanding_lazy_request);
>  	i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>  }
>  
> @@ -3114,8 +3124,6 @@ out:
>   *
>   * @obj: object which may be in use on another ring.
>   * @to: ring we wish to use the object on. May be NULL.
> - * @add_request: do we need to add a request to track operations
> - *    submitted on ring with sync_to function
>   *
>   * This code is meant to abstract object synchronization with the GPU.
>   * Calling with NULL implies synchronizing the object with the CPU
> @@ -3125,8 +3133,9 @@ out:
>   */
>  int
>  i915_gem_object_sync(struct drm_i915_gem_object *obj,
> -		     struct intel_engine_cs *to, bool add_request)
> +		     struct drm_i915_gem_request *to_req)
>  {
> +	struct intel_engine_cs *to = to_req->ring;
>  	struct intel_engine_cs *from;
>  	u32 seqno;
>  	int ret, idx;
> @@ -3152,7 +3161,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
>  		return ret;
>  
>  	trace_i915_gem_ring_sync_to(from, to, obj->last_read_req);
> -	ret = to->semaphore.sync_to(to, from, seqno);
> +	ret = to->semaphore.sync_to(to_req, from, seqno);
>  	if (!ret) {
>  		/* We use last_read_req because sync_to()
>  		 * might have just caused seqno wrap under
> @@ -3160,8 +3169,6 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
>  		 */
>  		from->semaphore.sync_seqno[idx] =
>  				i915_gem_request_get_seqno(obj->last_read_req);
> -		if (add_request)
> -			i915_add_request_no_flush(to);
>  	}
>  
>  	return ret;
> @@ -3266,18 +3273,23 @@ int i915_gpu_idle(struct drm_device *dev)
>  	/* Flush everything onto the inactive list. */
>  	for_each_ring(ring, dev_priv, i) {
>  		if (!i915.enable_execlists) {
> -			ret = i915_switch_context(ring, ring->default_context);
> +			struct drm_i915_gem_request *req;
> +
> +			ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
>  			if (ret)
>  				return ret;
> -		}
>  
> -		/* Make sure the context switch (if one actually happened)
> -		 * gets wrapped up and finished rather than hanging around
> -		 * and confusing things later. */
> -		if (ring->outstanding_lazy_request) {
> -			ret = i915_add_request(ring);
> -			if (ret)
> +			ret = i915_switch_context(req, ring->default_context);
> +			if (ret) {
> +				i915_gem_request_unreference(req);
>  				return ret;
> +			}
> +
> +			ret = i915_add_request_no_flush(req);
> +			if (ret) {
> +				i915_gem_request_unreference(req);
> +				return ret;
> +			}
>  		}
>  
>  		ret = intel_ring_idle(ring);
> @@ -4099,8 +4111,19 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
>  	bool was_pin_display;
>  	int ret;
>  
> -	if (pipelined != i915_gem_request_get_ring(obj->last_read_req)) {
> -		ret = i915_gem_object_sync(obj, pipelined, true);
> +	if (pipelined && (pipelined != i915_gem_request_get_ring(obj->last_read_req))) {
> +		struct drm_i915_private *dev_priv = pipelined->dev->dev_private;
> +		struct drm_i915_gem_request *req;
> +
> +		ret = dev_priv->gt.alloc_request(pipelined, pipelined->default_context, &req);
> +		if (ret)
> +			return ret;
> +
> +		ret = i915_gem_object_sync(obj, req);
> +		if (ret)
> +			return ret;
> +
> +		ret = i915_add_request_no_flush(req);
>  		if (ret)
>  			return ret;
>  	}
> @@ -4771,8 +4794,9 @@ err:
>  	return ret;
>  }
>  
> -int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
> +int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
> @@ -4782,7 +4806,7 @@ int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
>  	if (!HAS_L3_DPF(dev) || !remap_info)
>  		return 0;
>  
> -	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
> +	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
>  	if (ret)
>  		return ret;
>  
> @@ -4962,37 +4986,67 @@ i915_gem_init_hw(struct drm_device *dev)
>  	 */
>  	init_unused_rings(dev);
>  
> +	BUG_ON(!dev_priv->ring[RCS].default_context);
> +
> +	ret = i915_ppgtt_init_hw(dev);
> +	if (ret) {
> +		DRM_ERROR("PPGTT enable failed %d\n", ret);
> +		i915_gem_cleanup_ringbuffer(dev);
> +		return ret;
> +	}
> +
>  	for_each_ring(ring, dev_priv, i) {
> +		struct drm_i915_gem_request *req;
> +
>  		ret = ring->init_hw(ring);
>  		if (ret)
>  			return ret;
> -	}
>  
> -	for (i = 0; i < NUM_L3_SLICES(dev); i++)
> -		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
> +		if (!ring->default_context)
> +			continue;
>  
> -	/*
> -	 * XXX: Contexts should only be initialized once. Doing a switch to the
> -	 * default context switch however is something we'd like to do after
> -	 * reset or thaw (the latter may not actually be necessary for HW, but
> -	 * goes with our code better). Context switching requires rings (for
> -	 * the do_switch), but before enabling PPGTT. So don't move this.
> -	 */
> -	ret = i915_gem_context_enable(dev_priv);
> -	if (ret && ret != -EIO) {
> -		DRM_ERROR("Context enable failed %d\n", ret);
> -		i915_gem_cleanup_ringbuffer(dev);
> +		ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> +		if (ret)
> +			return ret;
>  
> -		return ret;
> -	}
> +		if (ring->id == RCS) {
> +			for (i = 0; i < NUM_L3_SLICES(dev); i++)
> +				i915_gem_l3_remap(req, i);
> +		}
>  
> -	ret = i915_ppgtt_init_hw(dev);
> -	if (ret && ret != -EIO) {
> -		DRM_ERROR("PPGTT enable failed %d\n", ret);
> -		i915_gem_cleanup_ringbuffer(dev);
> +		/*
> +		 * XXX: Contexts should only be initialized once. Doing a switch to the
> +		 * default context switch however is something we'd like to do after
> +		 * reset or thaw (the latter may not actually be necessary for HW, but
> +		 * goes with our code better). Context switching requires rings (for
> +		 * the do_switch), but before enabling PPGTT. So don't move this.
> +		 */
> +		ret = i915_gem_context_enable(req);
> +		if (ret && ret != -EIO) {
> +			DRM_ERROR("Context enable failed %d\n", ret);
> +			i915_gem_request_unreference(req);
> +			i915_gem_cleanup_ringbuffer(dev);
> +
> +			return ret;
> +		}
> +
> +		ret = i915_ppgtt_init_ring(req);
> +		if (ret && ret != -EIO) {
> +			DRM_ERROR("PPGTT enable failed %d\n", ret);
> +			i915_gem_request_unreference(req);
> +			i915_gem_cleanup_ringbuffer(dev);
> +		}
> +
> +		ret = i915_add_request_no_flush(req);
> +		if (ret) {
> +			DRM_ERROR("Add request failed: %d\n", ret);
> +			i915_gem_request_unreference(req);
> +			i915_gem_cleanup_ringbuffer(dev);
> +			return ret;
> +		}
>  	}
>  
> -	return ret;
> +	return 0;
>  }
>  
>  int i915_gem_init(struct drm_device *dev)
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
> index c5e1bfc..72e280b 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/i915_gem_context.c
> @@ -401,41 +401,23 @@ void i915_gem_context_fini(struct drm_device *dev)
>  	i915_gem_context_unreference(dctx);
>  }
>  
> -int i915_gem_context_enable(struct drm_i915_private *dev_priv)
> +int i915_gem_context_enable(struct drm_i915_gem_request *req)
>  {
> -	struct intel_engine_cs *ring;
> -	int ret, i;
> -
> -	BUG_ON(!dev_priv->ring[RCS].default_context);
> +	struct intel_engine_cs *ring = req->ring;
> +	int ret;
>  
>  	if (i915.enable_execlists) {
> -		for_each_ring(ring, dev_priv, i) {
> -			if (ring->init_context) {
> -				ret = ring->init_context(ring,
> -						ring->default_context);
> -				if (ret) {
> -					DRM_ERROR("ring init context: %d\n",
> -							ret);
> -					return ret;
> -				}
> -			}
> -		}
> +		if (ring->init_context == NULL)
> +			return 0;
>  
> +		ret = ring->init_context(req, ring->default_context);
>  	} else
> -		for_each_ring(ring, dev_priv, i) {
> -			ret = i915_switch_context(ring, ring->default_context);
> -			if (ret)
> -				return ret;
> -
> -			/* Make sure the context switch (if one actually happened)
> -			 * gets wrapped up and finished rather than hanging around
> -			 * and confusing things later. */
> -			if (ring->outstanding_lazy_request) {
> -				ret = i915_add_request_no_flush(ring);
> -				if (ret)
> -					return ret;
> -			}
> -		}
> +		ret = i915_switch_context(req, ring->default_context);
> +
> +	if (ret) {
> +		DRM_ERROR("ring init context: %d\n", ret);
> +		return ret;
> +	}
>  
>  	return 0;
>  }
> @@ -488,10 +470,11 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
>  }
>  
>  static inline int
> -mi_set_context(struct intel_engine_cs *ring,
> +mi_set_context(struct drm_i915_gem_request *req,
>  	       struct intel_context *new_context,
>  	       u32 hw_flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 flags = hw_flags | MI_MM_SPACE_GTT;
>  	int ret;
>  
> @@ -501,7 +484,7 @@ mi_set_context(struct intel_engine_cs *ring,
>  	 * itlb_before_ctx_switch.
>  	 */
>  	if (IS_GEN6(ring->dev)) {
> -		ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0);
> +		ret = ring->flush(req, I915_GEM_GPU_DOMAINS, 0);
>  		if (ret)
>  			return ret;
>  	}
> @@ -510,7 +493,7 @@ mi_set_context(struct intel_engine_cs *ring,
>  	if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
>  		flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -540,9 +523,10 @@ mi_set_context(struct intel_engine_cs *ring,
>  	return ret;
>  }
>  
> -static int do_switch(struct intel_engine_cs *ring,
> +static int do_switch(struct drm_i915_gem_request *req,
>  		     struct intel_context *to)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = ring->dev->dev_private;
>  	struct intel_context *from = ring->last_context;
>  	u32 hw_flags = 0;
> @@ -577,7 +561,7 @@ static int do_switch(struct intel_engine_cs *ring,
>  
>  	if (to->ppgtt) {
>  		trace_switch_mm(ring, to);
> -		ret = to->ppgtt->switch_mm(to->ppgtt, ring);
> +		ret = to->ppgtt->switch_mm(to->ppgtt, req);
>  		if (ret)
>  			goto unpin_out;
>  	}
> @@ -608,7 +592,7 @@ static int do_switch(struct intel_engine_cs *ring,
>  	if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
>  		hw_flags |= MI_RESTORE_INHIBIT;
>  
> -	ret = mi_set_context(ring, to, hw_flags);
> +	ret = mi_set_context(req, to, hw_flags);
>  	if (ret)
>  		goto unpin_out;
>  
> @@ -616,7 +600,7 @@ static int do_switch(struct intel_engine_cs *ring,
>  		if (!(to->remap_slice & (1<<i)))
>  			continue;
>  
> -		ret = i915_gem_l3_remap(ring, i);
> +		ret = i915_gem_l3_remap(req, i);
>  		/* If it failed, try again next round */
>  		if (ret)
>  			DRM_DEBUG_DRIVER("L3 remapping failed\n");
> @@ -632,7 +616,7 @@ static int do_switch(struct intel_engine_cs *ring,
>  	 */
>  	if (from != NULL) {
>  		from->legacy_hw_ctx.rcs_state->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
> -		i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), ring);
> +		i915_vma_move_to_active(i915_gem_obj_to_ggtt(from->legacy_hw_ctx.rcs_state), req);
>  		/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
>  		 * whole damn pipeline, we don't need to explicitly mark the
>  		 * object dirty. The only exception is that the context must be
> @@ -658,12 +642,12 @@ done:
>  
>  	if (uninitialized) {
>  		if (ring->init_context) {
> -			ret = ring->init_context(ring, to);
> +			ret = ring->init_context(req, to);
>  			if (ret)
>  				DRM_ERROR("ring init context: %d\n", ret);
>  		}
>  
> -		ret = i915_gem_render_state_init(ring);
> +		ret = i915_gem_render_state_init(req);
>  		if (ret)
>  			DRM_ERROR("init render state: %d\n", ret);
>  	}
> @@ -690,9 +674,10 @@ unpin_out:
>   * switched by writing to the ELSP and requests keep a reference to their
>   * context.
>   */
> -int i915_switch_context(struct intel_engine_cs *ring,
> +int i915_switch_context(struct drm_i915_gem_request *req,
>  			struct intel_context *to)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = ring->dev->dev_private;
>  
>  	WARN_ON(i915.enable_execlists);
> @@ -708,7 +693,7 @@ int i915_switch_context(struct intel_engine_cs *ring,
>  		return 0;
>  	}
>  
> -	return do_switch(ring, to);
> +	return do_switch(req, to);
>  }
>  
>  static bool contexts_enabled(struct drm_device *dev)
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index ca31673..5caa2a2 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -822,7 +822,7 @@ err:
>  }
>  
>  static int
> -i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
> +i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
>  				struct list_head *vmas)
>  {
>  	struct i915_vma *vma;
> @@ -832,7 +832,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
>  
>  	list_for_each_entry(vma, vmas, exec_list) {
>  		struct drm_i915_gem_object *obj = vma->obj;
> -		ret = i915_gem_object_sync(obj, ring, false);
> +		ret = i915_gem_object_sync(obj, req);
>  		if (ret)
>  			return ret;
>  
> @@ -843,7 +843,7 @@ i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
>  	}
>  
>  	if (flush_chipset)
> -		i915_gem_chipset_flush(ring->dev);
> +		i915_gem_chipset_flush(req->ring->dev);
>  
>  	if (flush_domains & I915_GEM_DOMAIN_GTT)
>  		wmb();
> @@ -941,9 +941,9 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
>  
>  void
>  i915_gem_execbuffer_move_to_active(struct list_head *vmas,
> -				   struct intel_engine_cs *ring)
> +				   struct drm_i915_gem_request *req)
>  {
> -	struct drm_i915_gem_request *req = intel_ring_get_request(ring);
> +	struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
>  	struct i915_vma *vma;
>  
>  	list_for_each_entry(vma, vmas, exec_list) {
> @@ -957,7 +957,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
>  			obj->base.pending_read_domains |= obj->base.read_domains;
>  		obj->base.read_domains = obj->base.pending_read_domains;
>  
> -		i915_vma_move_to_active(vma, ring);
> +		i915_vma_move_to_active(vma, req);
>  		if (obj->base.write_domain) {
>  			obj->dirty = 1;
>  			i915_gem_request_assign(&obj->last_write_req, req);
> @@ -983,20 +983,21 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
>  void
>  i915_gem_execbuffer_retire_commands(struct drm_device *dev,
>  				    struct drm_file *file,
> -				    struct intel_engine_cs *ring,
> +				    struct drm_i915_gem_request *req,
>  				    struct drm_i915_gem_object *obj)
>  {
>  	/* Unconditionally force add_request to emit a full flush. */
> -	ring->gpu_caches_dirty = true;
> +	req->ring->gpu_caches_dirty = true;
>  
>  	/* Add a breadcrumb for the completion of the batch buffer */
> -	(void)__i915_add_request(ring, file, obj, true);
> +	(void)__i915_add_request(req, file, obj, true);
>  }
>  
>  static int
>  i915_reset_gen7_sol_offsets(struct drm_device *dev,
> -			    struct intel_engine_cs *ring)
> +			    struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	int ret, i;
>  
> @@ -1005,7 +1006,7 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
>  		return -EINVAL;
>  	}
>  
> -	ret = intel_ring_begin(ring, 4 * 3);
> +	ret = intel_ring_begin(req, 4 * 3);
>  	if (ret)
>  		return ret;
>  
> @@ -1021,10 +1022,11 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
>  }
>  
>  static int
> -i915_emit_box(struct intel_engine_cs *ring,
> +i915_emit_box(struct drm_i915_gem_request *req,
>  	      struct drm_clip_rect *box,
>  	      int DR1, int DR4)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	if (box->y2 <= box->y1 || box->x2 <= box->x1 ||
> @@ -1035,7 +1037,7 @@ i915_emit_box(struct intel_engine_cs *ring,
>  	}
>  
>  	if (INTEL_INFO(ring->dev)->gen >= 4) {
> -		ret = intel_ring_begin(ring, 4);
> +		ret = intel_ring_begin(req, 4);
>  		if (ret)
>  			return ret;
>  
> @@ -1044,7 +1046,7 @@ i915_emit_box(struct intel_engine_cs *ring,
>  		intel_ring_emit(ring, ((box->x2 - 1) & 0xffff) | (box->y2 - 1) << 16);
>  		intel_ring_emit(ring, DR4);
>  	} else {
> -		ret = intel_ring_begin(ring, 6);
> +		ret = intel_ring_begin(req, 6);
>  		if (ret)
>  			return ret;
>  
> @@ -1151,11 +1153,11 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
>  		goto error;
>  	}
>  
> -	ret = i915_gem_execbuffer_move_to_gpu(ring, vmas);
> +	ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas);
>  	if (ret)
>  		goto error;
>  
> -	i915_gem_execbuffer_move_to_active(vmas, ring);
> +	i915_gem_execbuffer_move_to_active(vmas, params->request);
>  
>  	/* Make sure the OLR hasn't advanced (which would indicate a flush
>  	 * of the work in progress which in turn would be a Bad Thing). */
> @@ -1200,18 +1202,18 @@ int i915_gem_ringbuffer_submission_final(struct i915_execbuffer_params *params)
>  	/* Unconditionally invalidate gpu caches and ensure that we do flush
>  	 * any residual writes from the previous batch.
>  	 */
> -	ret = intel_ring_invalidate_all_caches(ring);
> +	ret = intel_ring_invalidate_all_caches(params->request);
>  	if (ret)
>  		goto error;
>  
>  	/* Switch to the correct context for the batch */
> -	ret = i915_switch_context(ring, params->ctx);
> +	ret = i915_switch_context(params->request, params->ctx);
>  	if (ret)
>  		goto error;
>  
>  	if (ring == &dev_priv->ring[RCS] &&
>  			params->instp_mode != dev_priv->relative_constants_mode) {
> -		ret = intel_ring_begin(ring, 4);
> +		ret = intel_ring_begin(params->request, 4);
>  		if (ret)
>  			goto error;
>  
> @@ -1225,7 +1227,7 @@ int i915_gem_ringbuffer_submission_final(struct i915_execbuffer_params *params)
>  	}
>  
>  	if (params->args_flags & I915_EXEC_GEN7_SOL_RESET) {
> -		ret = i915_reset_gen7_sol_offsets(params->dev, ring);
> +		ret = i915_reset_gen7_sol_offsets(params->dev, params->request);
>  		if (ret)
>  			goto error;
>  	}
> @@ -1236,29 +1238,31 @@ int i915_gem_ringbuffer_submission_final(struct i915_execbuffer_params *params)
>  
>  	if (params->cliprects) {
>  		for (i = 0; i < params->args_num_cliprects; i++) {
> -			ret = i915_emit_box(ring, &params->cliprects[i],
> -					    params->args_DR1, params->args_DR4);
> +			ret = i915_emit_box(params->request,
> +					    &params->cliprects[i],
> +					    params->args_DR1,
> +					    params->args_DR4);
>  			if (ret)
>  				goto error;
>  
> -			ret = ring->dispatch_execbuffer(ring,
> +			ret = ring->dispatch_execbuffer(params->request,
>  							exec_start, exec_len,
>  							params->dispatch_flags);
>  			if (ret)
>  				goto error;
>  		}
>  	} else {
> -		ret = ring->dispatch_execbuffer(ring,
> +		ret = ring->dispatch_execbuffer(params->request,
>  						exec_start, exec_len,
>  						params->dispatch_flags);
>  		if (ret)
>  			goto error;
>  	}
>  
> -	trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> +	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>  
> -	i915_gem_execbuffer_retire_commands(params->dev, params->file, ring,
> -					    params->batch_obj);
> +	i915_gem_execbuffer_retire_commands(params->dev, params->file,
> +					    params->request, params->batch_obj);
>  
>  error:
>  	/* intel_gpu_busy should also get a ref, so it will free when the device
> @@ -1490,10 +1494,10 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
>  		params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm);
>  
>  	/* Allocate a request for this batch buffer nice and early. */
> -	ret = dev_priv->gt.alloc_request(ring, ctx);
> +	ret = dev_priv->gt.alloc_request(ring, ctx, &params->request);
>  	if (ret)
>  		goto err;
> -	params->request = ring->outstanding_lazy_request;
> +	WARN_ON(params->request != ring->outstanding_lazy_request);
>  
>  	/* Save assorted stuff away to pass through to *_submission_final() */
>  	params->dev                     = dev;
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index 7eead93..776776e 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -213,14 +213,15 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
>  }
>  
>  /* Broadwell Page Directory Pointer Descriptors */
> -static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
> -			   uint64_t val)
> +static int gen8_write_pdp(struct drm_i915_gem_request *req, unsigned entry,
> +			  uint64_t val)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	BUG_ON(entry >= 4);
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -236,7 +237,7 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
>  }
>  
>  static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
> -			  struct intel_engine_cs *ring)
> +			  struct drm_i915_gem_request *req)
>  {
>  	int i, ret;
>  
> @@ -245,7 +246,7 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
>  
>  	for (i = used_pd - 1; i >= 0; i--) {
>  		dma_addr_t addr = ppgtt->pd_dma_addr[i];
> -		ret = gen8_write_pdp(ring, i, addr);
> +		ret = gen8_write_pdp(req, i, addr);
>  		if (ret)
>  			return ret;
>  	}
> @@ -710,16 +711,17 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
>  }
>  
>  static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> -			 struct intel_engine_cs *ring)
> +			 struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	/* NB: TLBs must be flushed and invalidated before a switch */
> -	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> +	ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
>  	if (ret)
>  		return ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -735,16 +737,17 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
>  }
>  
>  static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
> -			  struct intel_engine_cs *ring)
> +			  struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	/* NB: TLBs must be flushed and invalidated before a switch */
> -	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> +	ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
>  	if (ret)
>  		return ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -758,7 +761,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
>  
>  	/* XXX: RCS is the only one to auto invalidate the TLBs? */
>  	if (ring->id != RCS) {
> -		ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
> +		ret = ring->flush(req, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
>  		if (ret)
>  			return ret;
>  	}
> @@ -767,8 +770,9 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
>  }
>  
>  static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
> -			  struct intel_engine_cs *ring)
> +			  struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_device *dev = ppgtt->base.dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  
> @@ -1125,11 +1129,6 @@ int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
>  
>  int i915_ppgtt_init_hw(struct drm_device *dev)
>  {
> -	struct drm_i915_private *dev_priv = dev->dev_private;
> -	struct intel_engine_cs *ring;
> -	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> -	int i, ret = 0;
> -
>  	/* In the case of execlists, PPGTT is enabled by the context descriptor
>  	 * and the PDPs are contained within the context itself.  We don't
>  	 * need to do anything here. */
> @@ -1148,25 +1147,20 @@ int i915_ppgtt_init_hw(struct drm_device *dev)
>  	else
>  		WARN_ON(1);
>  
> -	if (ppgtt) {
> -		for_each_ring(ring, dev_priv, i) {
> -			ret = ppgtt->switch_mm(ppgtt, ring);
> -			if (ret != 0)
> -				return ret;
> -
> -			/* Make sure the context switch (if one actually happened)
> -			 * gets wrapped up and finished rather than hanging around
> -			 * and confusing things later. */
> -			if (ring->outstanding_lazy_request) {
> -				ret = i915_add_request_no_flush(ring);
> -				if (ret)
> -					return ret;
> -			}
> -		}
> -	}
> +	return 0;
> +}
>  
> -	return ret;
> +int i915_ppgtt_init_ring(struct drm_i915_gem_request *req)
> +{
> +	struct drm_i915_private *dev_priv = req->ring->dev->dev_private;
> +	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> +
> +	if (!ppgtt)
> +		return 0;
> +
> +	return ppgtt->switch_mm(ppgtt, req);
>  }
> +
>  struct i915_hw_ppgtt *
>  i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
>  {
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index dd849df..bee3e2a 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -267,7 +267,7 @@ struct i915_hw_ppgtt {
>  
>  	int (*enable)(struct i915_hw_ppgtt *ppgtt);
>  	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
> -			 struct intel_engine_cs *ring);
> +			 struct drm_i915_gem_request *req);
>  	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
>  };
>  
> @@ -278,6 +278,7 @@ void i915_global_gtt_cleanup(struct drm_device *dev);
>  
>  int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
>  int i915_ppgtt_init_hw(struct drm_device *dev);
> +int i915_ppgtt_init_ring(struct drm_i915_gem_request *req);
>  void i915_ppgtt_release(struct kref *kref);
>  struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
>  					struct drm_i915_file_private *fpriv);
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
> index aba39c3..0e0c23fe 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.c
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
> @@ -152,8 +152,9 @@ int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
>  	return 0;
>  }
>  
> -int i915_gem_render_state_init(struct intel_engine_cs *ring)
> +int i915_gem_render_state_init(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
>  	struct render_state so;
>  	int ret;
>  
> @@ -164,16 +165,17 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
>  	if (so.rodata == NULL)
>  		return 0;
>  
> -	ret = ring->dispatch_execbuffer(ring,
> +	ret = ring->dispatch_execbuffer(req,
>  					so.ggtt_offset,
>  					so.rodata->batch_items * 4,
>  					I915_DISPATCH_SECURE);
>  	if (ret)
>  		goto out;
>  
> -	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
> +	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
>  
> -	ret = __i915_add_request(ring, NULL, so.obj, true);
> +//	ret = __i915_add_request(req, NULL, so.obj, true);
> +	req->batch_obj = so.obj;
>  	/* __i915_add_request moves object to inactive if it fails */
>  out:
>  	i915_gem_render_state_fini(&so);
> diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
> index c44961e..7aa7372 100644
> --- a/drivers/gpu/drm/i915/i915_gem_render_state.h
> +++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
> @@ -39,7 +39,7 @@ struct render_state {
>  	int gen;
>  };
>  
> -int i915_gem_render_state_init(struct intel_engine_cs *ring);
> +int i915_gem_render_state_init(struct drm_i915_gem_request *req);
>  void i915_gem_render_state_fini(struct render_state *so);
>  int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
>  				  struct render_state *so);
> diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
> index f0cf421..c0b0e37 100644
> --- a/drivers/gpu/drm/i915/intel_display.c
> +++ b/drivers/gpu/drm/i915/intel_display.c
> @@ -9089,14 +9089,15 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	u32 flip_mask;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -9116,7 +9117,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, 0); /* aux display base address, unused */
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  	return 0;
>  }
>  
> @@ -9124,14 +9125,15 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	u32 flip_mask;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -9148,7 +9150,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, MI_NOOP);
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  	return 0;
>  }
>  
> @@ -9156,15 +9158,16 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	uint32_t pf, pipesrc;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -9187,7 +9190,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, pf | pipesrc);
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  	return 0;
>  }
>  
> @@ -9195,15 +9198,16 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	uint32_t pf, pipesrc;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -9223,7 +9227,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, pf | pipesrc);
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  	return 0;
>  }
>  
> @@ -9231,9 +9235,10 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	uint32_t plane_bit = 0;
>  	int len, ret;
> @@ -9275,11 +9280,11 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
>  	 * then do the cacheline alignment, and finally emit the
>  	 * MI_DISPLAY_FLIP.
>  	 */
> -	ret = intel_ring_cacheline_align(ring);
> +	ret = intel_ring_cacheline_align(req);
>  	if (ret)
>  		return ret;
>  
> -	ret = intel_ring_begin(ring, len);
> +	ret = intel_ring_begin(req, len);
>  	if (ret)
>  		return ret;
>  
> @@ -9318,7 +9323,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, (MI_NOOP));
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  	return 0;
>  }
>  
> @@ -9474,9 +9479,10 @@ static int intel_gen9_queue_flip(struct drm_device *dev,
>  				 struct drm_crtc *crtc,
>  				 struct drm_framebuffer *fb,
>  				 struct drm_i915_gem_object *obj,
> -				 struct intel_engine_cs *ring,
> +				 struct drm_i915_gem_request *req,
>  				 uint32_t flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
>  	uint32_t plane = 0, stride;
>  	int ret;
> @@ -9508,7 +9514,7 @@ static int intel_gen9_queue_flip(struct drm_device *dev,
>  		return -ENODEV;
>  	}
>  
> -	ret = intel_ring_begin(ring, 10);
> +	ret = intel_ring_begin(req, 10);
>  	if (ret)
>  		return ret;
>  
> @@ -9528,7 +9534,7 @@ static int intel_gen9_queue_flip(struct drm_device *dev,
>  	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
>  
>  	intel_mark_page_flip_active(intel_crtc);
> -	i915_add_request_no_flush(ring);
> +	i915_add_request_no_flush(req);
>  
>  	return 0;
>  }
> @@ -9537,7 +9543,7 @@ static int intel_default_queue_flip(struct drm_device *dev,
>  				    struct drm_crtc *crtc,
>  				    struct drm_framebuffer *fb,
>  				    struct drm_i915_gem_object *obj,
> -				    struct intel_engine_cs *ring,
> +				    struct drm_i915_gem_request *req,
>  				    uint32_t flags)
>  {
>  	return -ENODEV;
> @@ -9729,22 +9735,18 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
>  		i915_gem_request_assign(&work->flip_queued_req,
>  					obj->last_write_req);
>  	} else {
> -		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
> +		struct drm_i915_gem_request *req;
> +
> +		ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> +		if (ret)
> +			return ret;
> +
> +		i915_gem_request_assign(&work->flip_queued_req, req);
> +
> +		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, req,
>  						   page_flip_flags);
>  		if (ret)
>  			goto cleanup_unpin;
> -
> -		/* Borked: need to get the seqno for the request submitted in
> -		 * 'queue_flip()' above. However, either the request has been
> -		 * posted already and the seqno is gone (q_f calls add_request),
> -		 * or the request never gets posted and is merged into whatever
> -		 * render comes along next (q_f calls ring_advance).
> -		 *
> -		 * On the other hand, seqnos are going away soon anyway! So
> -		 * hopefully the problem will disappear...
> -		 */
> -		i915_gem_request_assign(&work->flip_queued_req,
> -					ring->outstanding_lazy_request ? intel_ring_get_request(ring) : NULL);
>  	}
>  
>  	work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 80cb87e..5077a77 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -203,6 +203,10 @@ enum {
>  };
>  #define GEN8_CTX_ID_SHIFT 32
>  
> +static int intel_logical_ring_begin(struct drm_i915_gem_request *req,
> +				    int num_dwords);
> +static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req,
> +					      struct intel_context *ctx);
>  static int intel_lr_context_pin(struct intel_engine_cs *ring,
>  		struct intel_context *ctx);
>  
> @@ -587,9 +591,9 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
>  	return 0;
>  }
>  
> -static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf)
> +static int logical_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
>  {
> -	struct intel_engine_cs *ring = ringbuf->ring;
> +	struct intel_engine_cs *ring = req->ring;
>  	uint32_t flush_domains;
>  	int ret;
>  
> @@ -597,7 +601,7 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf)
>  	if (ring->gpu_caches_dirty)
>  		flush_domains = I915_GEM_GPU_DOMAINS;
>  
> -	ret = ring->emit_flush(ringbuf, I915_GEM_GPU_DOMAINS, flush_domains);
> +	ret = ring->emit_flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
>  	if (ret)
>  		return ret;
>  
> @@ -605,10 +609,9 @@ static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf)
>  	return 0;
>  }
>  
> -static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
> +static int execlists_move_to_gpu(struct drm_i915_gem_request *req,
>  				 struct list_head *vmas)
>  {
> -	struct intel_engine_cs *ring = ringbuf->ring;
>  	struct i915_vma *vma;
>  	uint32_t flush_domains = 0;
>  	bool flush_chipset = false;
> @@ -617,7 +620,7 @@ static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
>  	list_for_each_entry(vma, vmas, exec_list) {
>  		struct drm_i915_gem_object *obj = vma->obj;
>  
> -		ret = i915_gem_object_sync(obj, ring, true);
> +		ret = i915_gem_object_sync(obj, req);
>  		if (ret)
>  			return ret;
>  
> @@ -657,7 +660,6 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
>  	struct drm_device       *dev = params->dev;
>  	struct intel_engine_cs  *ring = params->ring;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
> -	struct intel_ringbuffer *ringbuf = params->ctx->engine[ring->id].ringbuf;
>  	int ret;
>  
>  	params->instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
> @@ -706,11 +708,11 @@ int intel_execlists_submission(struct i915_execbuffer_params *params,
>  		return -EINVAL;
>  	}
>  
> -	ret = execlists_move_to_gpu(ringbuf, vmas);
> +	ret = execlists_move_to_gpu(params->request, vmas);
>  	if (ret)
>  		return ret;
>  
> -	i915_gem_execbuffer_move_to_active(vmas, ring);
> +	i915_gem_execbuffer_move_to_active(vmas, params->request);
>  
>  	ret = dev_priv->gt.do_execfinal(params);
>  	if (ret)
> @@ -742,13 +744,13 @@ int intel_execlists_submission_final(struct i915_execbuffer_params *params)
>  	/* Unconditionally invalidate gpu caches and ensure that we do flush
>  	 * any residual writes from the previous batch.
>  	 */
> -	ret = logical_ring_invalidate_all_caches(ringbuf);
> +	ret = logical_ring_invalidate_all_caches(params->request);
>  	if (ret)
>  		return ret;
>  
>  	if (ring == &dev_priv->ring[RCS] &&
>  	    params->instp_mode != dev_priv->relative_constants_mode) {
> -		ret = intel_logical_ring_begin(ringbuf, 4);
> +		ret = intel_logical_ring_begin(params->request, 4);
>  		if (ret)
>  			return ret;
>  
> @@ -764,13 +766,14 @@ int intel_execlists_submission_final(struct i915_execbuffer_params *params)
>  	exec_start = params->batch_obj_vm_offset +
>  		     params->args_batch_start_offset;
>  
> -	ret = ring->emit_bb_start(ringbuf, exec_start, params->dispatch_flags);
> +	ret = ring->emit_bb_start(params->request, exec_start, params->dispatch_flags);
>  	if (ret)
>  		return ret;
>  
> -	trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), params->dispatch_flags);
> +	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
>  
> -	i915_gem_execbuffer_retire_commands(params->dev, params->file, ring, params->batch_obj);
> +	i915_gem_execbuffer_retire_commands(params->dev, params->file,
> +					    params->request, params->batch_obj);
>  
>  	return 0;
>  }
> @@ -827,15 +830,15 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring)
>  	I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
>  }
>  
> -int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf)
> +int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
>  {
> -	struct intel_engine_cs *ring = ringbuf->ring;
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	if (!ring->gpu_caches_dirty)
>  		return 0;
>  
> -	ret = ring->emit_flush(ringbuf, 0, I915_GEM_GPU_DOMAINS);
> +	ret = ring->emit_flush(req, 0, I915_GEM_GPU_DOMAINS);
>  	if (ret)
>  		return ret;
>  
> @@ -910,13 +913,17 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
>  }
>  
>  int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> -				     struct intel_context *ctx)
> +				     struct intel_context *ctx,
> +				     struct drm_i915_gem_request **req_out)
>  {
>  	struct drm_i915_gem_request *request;
>  	struct drm_i915_private *dev_private = ring->dev->dev_private;
>  	int ret;
>  
> -	if (ring->outstanding_lazy_request)
> +	if (!req_out)
> +		return -EINVAL;
> +
> +	if ((*req_out = ring->outstanding_lazy_request) != NULL)
>  		return 0;
>  
>  	request = kzalloc(sizeof(*request), GFP_KERNEL);
> @@ -953,7 +960,7 @@ int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
>  	i915_gem_context_reference(request->ctx);
>  	request->ringbuf = ctx->engine[ring->id].ringbuf;
>  
> -	ring->outstanding_lazy_request = request;
> +	*req_out = ring->outstanding_lazy_request = request;
>  	return 0;
>  }
>  
> @@ -1090,7 +1097,7 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf, int bytes)
>  /**
>   * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
>   *
> - * @ringbuf: Logical ringbuffer.
> + * @request: The request to start some new work for
>   * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
>   *
>   * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
> @@ -1100,8 +1107,9 @@ static int logical_ring_prepare(struct intel_ringbuffer *ringbuf, int bytes)
>   *
>   * Return: non-zero if the ringbuffer is not ready to be written to.
>   */
> -int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords)
> +static int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
>  {
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
>  	struct intel_engine_cs *ring = ringbuf->ring;
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -1116,38 +1124,28 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords)
>  	if (ret)
>  		return ret;
>  
> -	if(!ring->outstanding_lazy_request) {
> -		printk(KERN_INFO "%s:%d> \x1B[31;1mring->outstanding_lazy_request = 0x%p\x1B[0m\n", __func__, __LINE__, ring->outstanding_lazy_request);
> -		dump_stack();
> -	}
> -
> -	/* Preallocate the olr before touching the ring */
> -	ret = intel_logical_ring_alloc_request(ring, ringbuf->FIXME_lrc_ctx);
> -	if (ret)
> -		return ret;
> -
>  	ringbuf->space -= num_dwords * sizeof(uint32_t);
>  	return 0;
>  }
>  
> -static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
> +static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req,
>  					       struct intel_context *ctx)
>  {
>  	int ret, i;
> -	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> -	struct drm_device *dev = ring->dev;
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
> +	struct drm_device *dev = req->ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct i915_workarounds *w = &dev_priv->workarounds;
>  
>  	if (WARN_ON(w->count == 0))
>  		return 0;
>  
> -	ring->gpu_caches_dirty = true;
> -	ret = logical_ring_flush_all_caches(ringbuf);
> +	req->ring->gpu_caches_dirty = true;
> +	ret = logical_ring_flush_all_caches(req);
>  	if (ret)
>  		return ret;
>  
> -	ret = intel_logical_ring_begin(ringbuf, w->count * 2 + 2);
> +	ret = intel_logical_ring_begin(req, w->count * 2 + 2);
>  	if (ret)
>  		return ret;
>  
> @@ -1160,8 +1158,8 @@ static int intel_logical_ring_workarounds_emit(struct intel_engine_cs *ring,
>  
>  	intel_logical_ring_advance(ringbuf);
>  
> -	ring->gpu_caches_dirty = true;
> -	ret = logical_ring_flush_all_caches(ringbuf);
> +	req->ring->gpu_caches_dirty = true;
> +	ret = logical_ring_flush_all_caches(req);
>  	if (ret)
>  		return ret;
>  
> @@ -1210,13 +1208,14 @@ static int gen8_init_render_ring(struct intel_engine_cs *ring)
>  	return init_workarounds_ring(ring);
>  }
>  
> -static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
> +static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
>  			      u64 offset, unsigned flags)
>  {
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
>  	bool ppgtt = !(flags & I915_DISPATCH_SECURE);
>  	int ret;
>  
> -	ret = intel_logical_ring_begin(ringbuf, 4);
> +	ret = intel_logical_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -1263,17 +1262,18 @@ static void gen8_logical_ring_put_irq(struct intel_engine_cs *ring)
>  	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
>  }
>  
> -static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
> +static int gen8_emit_flush(struct drm_i915_gem_request *req,
>  			   u32 invalidate_domains,
>  			   u32 unused)
>  {
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
>  	struct intel_engine_cs *ring = ringbuf->ring;
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	uint32_t cmd;
>  	int ret;
>  
> -	ret = intel_logical_ring_begin(ringbuf, 4);
> +	ret = intel_logical_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -1301,10 +1301,11 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
>  	return 0;
>  }
>  
> -static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
> +static int gen8_emit_flush_render(struct drm_i915_gem_request *req,
>  				  u32 invalidate_domains,
>  				  u32 flush_domains)
>  {
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
>  	struct intel_engine_cs *ring = ringbuf->ring;
>  	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	u32 flags = 0;
> @@ -1328,7 +1329,7 @@ static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
>  		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
>  	}
>  
> -	ret = intel_logical_ring_begin(ringbuf, 6);
> +	ret = intel_logical_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -1353,13 +1354,14 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
>  	intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
>  }
>  
> -static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
> +static int gen8_emit_request(struct drm_i915_gem_request *req)
>  {
> +	struct intel_ringbuffer *ringbuf = req->ringbuf;
>  	struct intel_engine_cs *ring = ringbuf->ring;
>  	u32 cmd;
>  	int ret;
>  
> -	ret = intel_logical_ring_begin(ringbuf, 6);
> +	ret = intel_logical_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -1371,8 +1373,7 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
>  				(ring->status_page.gfx_addr +
>  				(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
>  	intel_logical_ring_emit(ringbuf, 0);
> -	intel_logical_ring_emit(ringbuf,
> -		i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> +	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(req));
>  	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
>  	intel_logical_ring_emit(ringbuf, MI_NOOP);
>  	intel_logical_ring_advance_and_submit(ringbuf);
> @@ -1380,16 +1381,20 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
>  	return 0;
>  }
>  
> -static int gen8_init_rcs_context(struct intel_engine_cs *ring,
> -		       struct intel_context *ctx)
> +static int gen8_init_rcs_context(struct drm_i915_gem_request *req,
> +				 struct intel_context *ctx)
>  {
>  	int ret;
>  
> -	ret = intel_logical_ring_workarounds_emit(ring, ctx);
> +	ret = intel_logical_ring_workarounds_emit(req, ctx);
>  	if (ret)
>  		return ret;
>  
> -	return intel_lr_context_render_state_init(ring, ctx);
> +	ret = intel_lr_context_render_state_init(req, ctx);
> +	if (ret)
> +		return ret;
> +
> +	return 0;
>  }
>  
>  /**
> @@ -1409,6 +1414,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
>  
>  	intel_logical_ring_stop(ring);
>  	WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
> +	WARN_ON(ring->outstanding_lazy_request);
>  	i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>  
>  	if (ring->cleanup)
> @@ -1648,10 +1654,10 @@ cleanup_render_ring:
>  	return ret;
>  }
>  
> -int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
> -				       struct intel_context *ctx)
> +static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req,
> +					      struct intel_context *ctx)
>  {
> -	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
> +	struct intel_engine_cs *ring = i915_gem_request_get_ring(req);
>  	struct render_state so;
>  	struct drm_i915_file_private *file_priv = ctx->file_priv;
>  	struct drm_file *file = file_priv ? file_priv->file : NULL;
> @@ -1664,15 +1670,13 @@ int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
>  	if (so.rodata == NULL)
>  		return 0;
>  
> -	ret = ring->emit_bb_start(ringbuf,
> -			so.ggtt_offset,
> -			I915_DISPATCH_SECURE);
> +	ret = ring->emit_bb_start(req, so.ggtt_offset, I915_DISPATCH_SECURE);
>  	if (ret)
>  		goto out;
>  
> -	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
> +	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req);
>  
> -	ret = __i915_add_request(ring, file, so.obj, true);
> +	ret = __i915_add_request(req, file, so.obj, true);
>  	/* intel_logical_ring_add_request moves object to inactive if it
>  	 * fails */
>  out:
> @@ -1883,6 +1887,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
>  int intel_lr_context_deferred_create(struct intel_context *ctx,
>  				     struct intel_engine_cs *ring)
>  {
> +	struct drm_i915_private *dev_priv = ring->dev->dev_private;
>  	const bool is_global_default_ctx = (ctx == ring->default_context);
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_gem_object *ctx_obj;
> @@ -1964,13 +1969,27 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
>  		lrc_setup_hardware_status_page(ring, ctx_obj);
>  	else if (ring->id == RCS && !ctx->rcs_initialized) {
>  		if (ring->init_context) {
> -			ret = ring->init_context(ring, ctx);
> +			struct drm_i915_gem_request *req;
> +
> +			ret = dev_priv->gt.alloc_request(ring, ctx, &req);
> +			if (ret)
> +				return ret;
> +
> +			ret = ring->init_context(req, ctx);
>  			if (ret) {
>  				DRM_ERROR("ring init context: %d\n", ret);
> +				i915_gem_request_unreference(req);
>  				ctx->engine[ring->id].ringbuf = NULL;
>  				ctx->engine[ring->id].state = NULL;
>  				goto error;
>  			}
> +
> +			ret = i915_add_request_no_flush(req);
> +			if (ret) {
> +				DRM_ERROR("ring init context: %d\n", ret);
> +				i915_gem_request_unreference(req);
> +				goto error;
> +			}
>  		}
>  
>  		ctx->rcs_initialized = true;
> diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
> index ea083d9..a2981ba 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.h
> +++ b/drivers/gpu/drm/i915/intel_lrc.h
> @@ -35,12 +35,13 @@
>  
>  /* Logical Rings */
>  int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
> -						  struct intel_context *ctx);
> +						  struct intel_context *ctx,
> +						  struct drm_i915_gem_request **req_out);
>  void intel_logical_ring_stop(struct intel_engine_cs *ring);
>  void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
>  int intel_logical_rings_init(struct drm_device *dev);
>  
> -int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf);
> +int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
>  void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf);
>  /**
>   * intel_logical_ring_advance() - advance the ringbuffer tail
> @@ -63,11 +64,8 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
>  	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
>  	ringbuf->tail += 4;
>  }
> -int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords);
>  
>  /* Logical Ring Contexts */
> -int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
> -				       struct intel_context *ctx);
>  void intel_lr_context_free(struct intel_context *ctx);
>  int intel_lr_context_deferred_create(struct intel_context *ctx,
>  				     struct intel_engine_cs *ring);
> diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
> index 973c9de..2d2ce59 100644
> --- a/drivers/gpu/drm/i915/intel_overlay.c
> +++ b/drivers/gpu/drm/i915/intel_overlay.c
> @@ -209,17 +209,15 @@ static void intel_overlay_unmap_regs(struct intel_overlay *overlay,
>  }
>  
>  static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
> +					 struct drm_i915_gem_request *req,
>  					 void (*tail)(struct intel_overlay *))
>  {
>  	struct drm_device *dev = overlay->dev;
> -	struct drm_i915_private *dev_priv = dev->dev_private;
> -	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
>  	int ret;
>  
>  	BUG_ON(overlay->last_flip_req);
> -	i915_gem_request_assign(&overlay->last_flip_req,
> -					     ring->outstanding_lazy_request);
> -	ret = i915_add_request(ring);
> +	i915_gem_request_assign(&overlay->last_flip_req, req);
> +	ret = i915_add_request(overlay->last_flip_req);
>  	if (ret)
>  		return ret;
>  
> @@ -239,6 +237,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
>  	struct drm_device *dev = overlay->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> +	struct drm_i915_gem_request *req;
>  	int ret;
>  
>  	BUG_ON(overlay->active);
> @@ -246,17 +245,21 @@ static int intel_overlay_on(struct intel_overlay *overlay)
>  
>  	WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE));
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
>  	if (ret)
>  		return ret;
>  
> -	intel_ring_emit(ring, MI_OVERLAY_FLIP | MI_OVERLAY_ON);
> -	intel_ring_emit(ring, overlay->flip_addr | OFC_UPDATE);
> -	intel_ring_emit(ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
> -	intel_ring_emit(ring, MI_NOOP);
> -	intel_ring_advance(ring);
> +	ret = intel_ring_begin(req, 4);
> +	if (ret)
> +		return ret;
> +
> +	intel_ring_emit(req->ring, MI_OVERLAY_FLIP | MI_OVERLAY_ON);
> +	intel_ring_emit(req->ring, overlay->flip_addr | OFC_UPDATE);
> +	intel_ring_emit(req->ring, MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
> +	intel_ring_emit(req->ring, MI_NOOP);
> +	intel_ring_advance(req->ring);
>  
> -	return intel_overlay_do_wait_request(overlay, NULL);
> +	return intel_overlay_do_wait_request(overlay, req, NULL);
>  }
>  
>  /* overlay needs to be enabled in OCMD reg */
> @@ -266,6 +269,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
>  	struct drm_device *dev = overlay->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> +	struct drm_i915_gem_request *req;
>  	u32 flip_addr = overlay->flip_addr;
>  	u32 tmp;
>  	int ret;
> @@ -280,7 +284,11 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
>  	if (tmp & (1 << 17))
>  		DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> +	if (ret)
> +		return ret;
> +
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -289,9 +297,8 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
>  	intel_ring_advance(ring);
>  
>  	WARN_ON(overlay->last_flip_req);
> -	i915_gem_request_assign(&overlay->last_flip_req,
> -					     ring->outstanding_lazy_request);
> -	return i915_add_request(ring);
> +	i915_gem_request_assign(&overlay->last_flip_req, req);
> +	return i915_add_request(req);
>  }
>  
>  static void intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)
> @@ -326,6 +333,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
>  	struct drm_device *dev = overlay->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> +	struct drm_i915_gem_request *req;
>  	u32 flip_addr = overlay->flip_addr;
>  	int ret;
>  
> @@ -337,7 +345,11 @@ static int intel_overlay_off(struct intel_overlay *overlay)
>  	 * of the hw. Do it in both cases */
>  	flip_addr |= OFC_UPDATE;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> +	if (ret)
> +		return ret;
> +
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -359,7 +371,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
>  	}
>  	intel_ring_advance(ring);
>  
> -	return intel_overlay_do_wait_request(overlay, intel_overlay_off_tail);
> +	return intel_overlay_do_wait_request(overlay, req, intel_overlay_off_tail);
>  }
>  
>  /* recover from an interruption due to a signal
> @@ -404,7 +416,13 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
>  
>  	if (I915_READ(ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT) {
>  		/* synchronous slowpath */
> -		ret = intel_ring_begin(ring, 2);
> +		struct drm_i915_gem_request *req;
> +
> +		ret = dev_priv->gt.alloc_request(ring, ring->default_context, &req);
> +		if (ret)
> +			return ret;
> +
> +		ret = intel_ring_begin(req, 2);
>  		if (ret)
>  			return ret;
>  
> @@ -412,7 +430,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
>  		intel_ring_emit(ring, MI_NOOP);
>  		intel_ring_advance(ring);
>  
> -		ret = intel_overlay_do_wait_request(overlay,
> +		ret = intel_overlay_do_wait_request(overlay, req,
>  						    intel_overlay_release_old_vid_tail);
>  		if (ret)
>  			return ret;
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 78911e2..5905fa5 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -5506,6 +5506,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
>  {
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
> +	struct drm_i915_gem_request *req = NULL;
>  	bool was_interruptible;
>  	int ret;
>  
> @@ -5524,16 +5525,17 @@ static void ironlake_enable_rc6(struct drm_device *dev)
>  	was_interruptible = dev_priv->mm.interruptible;
>  	dev_priv->mm.interruptible = false;
>  
> +	ret = dev_priv->gt.alloc_request(ring, NULL, &req);
> +	if (ret)
> +		goto err;
> +
>  	/*
>  	 * GPU can automatically power down the render unit if given a page
>  	 * to save state.
>  	 */
> -	ret = intel_ring_begin(ring, 6);
> -	if (ret) {
> -		ironlake_teardown_rc6(dev);
> -		dev_priv->mm.interruptible = was_interruptible;
> -		return;
> -	}
> +	ret = intel_ring_begin(req, 6);
> +	if (ret)
> +		goto err;
>  
>  	intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
>  	intel_ring_emit(ring, MI_SET_CONTEXT);
> @@ -5547,6 +5549,11 @@ static void ironlake_enable_rc6(struct drm_device *dev)
>  	intel_ring_emit(ring, MI_FLUSH);
>  	intel_ring_advance(ring);
>  
> +	ret = i915_add_request_no_flush(req);
> +	if (ret)
> +		goto err;
> +	req = NULL;
> +
>  	/*
>  	 * Wait for the command parser to advance past MI_SET_CONTEXT. The HW
>  	 * does an implicit flush, combined with MI_FLUSH above, it should be
> @@ -5554,16 +5561,20 @@ static void ironlake_enable_rc6(struct drm_device *dev)
>  	 */
>  	ret = intel_ring_idle(ring);
>  	dev_priv->mm.interruptible = was_interruptible;
> -	if (ret) {
> -		DRM_ERROR("failed to enable ironlake power savings\n");
> -		ironlake_teardown_rc6(dev);
> -		return;
> -	}
> +	if (ret)
> +		goto err;
>  
>  	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
>  	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
>  
>  	intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
> +
> +err:
> +	DRM_ERROR("failed to enable ironlake power savings\n");
> +	ironlake_teardown_rc6(dev);
> +	dev_priv->mm.interruptible = was_interruptible;
> +	if (req)
> +		i915_gem_request_unreference(req);
>  }
>  
>  static unsigned long intel_pxfreq(u32 vidfreq)
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index b60e59b..e6e7bb5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -91,10 +91,11 @@ void __intel_ring_advance(struct intel_engine_cs *ring)
>  }
>  
>  static int
> -gen2_render_ring_flush(struct intel_engine_cs *ring,
> +gen2_render_ring_flush(struct drm_i915_gem_request *req,
>  		       u32	invalidate_domains,
>  		       u32	flush_domains)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 cmd;
>  	int ret;
>  
> @@ -105,7 +106,7 @@ gen2_render_ring_flush(struct intel_engine_cs *ring,
>  	if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
>  		cmd |= MI_READ_FLUSH;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -117,10 +118,11 @@ gen2_render_ring_flush(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -gen4_render_ring_flush(struct intel_engine_cs *ring,
> +gen4_render_ring_flush(struct drm_i915_gem_request *req,
>  		       u32	invalidate_domains,
>  		       u32	flush_domains)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_device *dev = ring->dev;
>  	u32 cmd;
>  	int ret;
> @@ -163,7 +165,7 @@ gen4_render_ring_flush(struct intel_engine_cs *ring,
>  	    (IS_G4X(dev) || IS_GEN5(dev)))
>  		cmd |= MI_INVALIDATE_ISP;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -212,12 +214,13 @@ gen4_render_ring_flush(struct intel_engine_cs *ring,
>   * really our business.  That leaves only stall at scoreboard.
>   */
>  static int
> -intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
> +intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -230,7 +233,7 @@ intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
>  	intel_ring_emit(ring, MI_NOOP);
>  	intel_ring_advance(ring);
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -246,15 +249,16 @@ intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
>  }
>  
>  static int
> -gen6_render_ring_flush(struct intel_engine_cs *ring,
> -                         u32 invalidate_domains, u32 flush_domains)
> +gen6_render_ring_flush(struct drm_i915_gem_request *req,
> +                       u32 invalidate_domains, u32 flush_domains)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 flags = 0;
>  	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	int ret;
>  
>  	/* Force SNB workarounds for PIPE_CONTROL flushes */
> -	ret = intel_emit_post_sync_nonzero_flush(ring);
> +	ret = intel_emit_post_sync_nonzero_flush(req);
>  	if (ret)
>  		return ret;
>  
> @@ -284,7 +288,7 @@ gen6_render_ring_flush(struct intel_engine_cs *ring,
>  		flags |= PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL;
>  	}
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -298,11 +302,12 @@ gen6_render_ring_flush(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
> +gen7_render_ring_cs_stall_wa(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -316,14 +321,15 @@ gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
>  	return 0;
>  }
>  
> -static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
> +static int gen7_ring_fbc_flush(struct drm_i915_gem_request *req, u32 value)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	if (!ring->fbc_dirty)
>  		return 0;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  	/* WaFbcNukeOn3DBlt:ivb/hsw */
> @@ -340,9 +346,10 @@ static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
>  }
>  
>  static int
> -gen7_render_ring_flush(struct intel_engine_cs *ring,
> +gen7_render_ring_flush(struct drm_i915_gem_request *req,
>  		       u32 invalidate_domains, u32 flush_domains)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 flags = 0;
>  	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	int ret;
> @@ -381,10 +388,10 @@ gen7_render_ring_flush(struct intel_engine_cs *ring,
>  		/* Workaround: we must issue a pipe_control with CS-stall bit
>  		 * set before a pipe_control command that has the state cache
>  		 * invalidate bit set. */
> -		gen7_render_ring_cs_stall_wa(ring);
> +		gen7_render_ring_cs_stall_wa(req);
>  	}
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -395,18 +402,19 @@ gen7_render_ring_flush(struct intel_engine_cs *ring,
>  	intel_ring_advance(ring);
>  
>  	if (!invalidate_domains && flush_domains)
> -		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
> +		return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
>  
>  	return 0;
>  }
>  
>  static int
> -gen8_emit_pipe_control(struct intel_engine_cs *ring,
> +gen8_emit_pipe_control(struct drm_i915_gem_request *req,
>  		       u32 flags, u32 scratch_addr)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -422,11 +430,11 @@ gen8_emit_pipe_control(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -gen8_render_ring_flush(struct intel_engine_cs *ring,
> +gen8_render_ring_flush(struct drm_i915_gem_request *req,
>  		       u32 invalidate_domains, u32 flush_domains)
>  {
>  	u32 flags = 0;
> -	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
> +	u32 scratch_addr = req->ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	int ret;
>  
>  	flags |= PIPE_CONTROL_CS_STALL;
> @@ -446,7 +454,7 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
>  		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
>  
>  		/* WaCsStallBeforeStateCacheInvalidate:bdw,chv */
> -		ret = gen8_emit_pipe_control(ring,
> +		ret = gen8_emit_pipe_control(req,
>  					     PIPE_CONTROL_CS_STALL |
>  					     PIPE_CONTROL_STALL_AT_SCOREBOARD,
>  					     0);
> @@ -454,12 +462,12 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
>  			return ret;
>  	}
>  
> -	ret = gen8_emit_pipe_control(ring, flags, scratch_addr);
> +	ret = gen8_emit_pipe_control(req, flags, scratch_addr);
>  	if (ret)
>  		return ret;
>  
>  	if (!invalidate_domains && flush_domains)
> -		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
> +		return gen7_ring_fbc_flush(req, FBC_REND_NUKE);
>  
>  	return 0;
>  }
> @@ -670,9 +678,10 @@ err:
>  	return ret;
>  }
>  
> -static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
> +static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req,
>  				       struct intel_context *ctx)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret, i;
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -682,11 +691,11 @@ static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
>  		return 0;
>  
>  	ring->gpu_caches_dirty = true;
> -	ret = intel_ring_flush_all_caches(ring);
> +	ret = intel_ring_flush_all_caches(req);
>  	if (ret)
>  		return ret;
>  
> -	ret = intel_ring_begin(ring, (w->count * 2 + 2));
> +	ret = intel_ring_begin(req, (w->count * 2 + 2));
>  	if (ret)
>  		return ret;
>  
> @@ -700,7 +709,7 @@ static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
>  	intel_ring_advance(ring);
>  
>  	ring->gpu_caches_dirty = true;
> -	ret = intel_ring_flush_all_caches(ring);
> +	ret = intel_ring_flush_all_caches(req);
>  	if (ret)
>  		return ret;
>  
> @@ -898,10 +907,11 @@ static void render_ring_cleanup(struct intel_engine_cs *ring)
>  	intel_fini_pipe_control(ring);
>  }
>  
> -static int gen8_rcs_signal(struct intel_engine_cs *signaller,
> +static int gen8_rcs_signal(struct drm_i915_gem_request *signaller_req,
>  			   unsigned int num_dwords)
>  {
>  #define MBOX_UPDATE_DWORDS 8
> +	struct intel_engine_cs *signaller = signaller_req->ring;
>  	struct drm_device *dev = signaller->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *waiter;
> @@ -911,7 +921,7 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
>  	num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
>  #undef MBOX_UPDATE_DWORDS
>  
> -	ret = intel_ring_begin(signaller, num_dwords);
> +	ret = intel_ring_begin(signaller_req, num_dwords);
>  	if (ret)
>  		return ret;
>  
> @@ -921,8 +931,7 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
>  		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
>  			continue;
>  
> -		seqno = i915_gem_request_get_seqno(
> -					   signaller->outstanding_lazy_request);
> +		seqno = i915_gem_request_get_seqno(signaller_req);
>  		intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
>  		intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
>  					   PIPE_CONTROL_QW_WRITE |
> @@ -939,10 +948,11 @@ static int gen8_rcs_signal(struct intel_engine_cs *signaller,
>  	return 0;
>  }
>  
> -static int gen8_xcs_signal(struct intel_engine_cs *signaller,
> +static int gen8_xcs_signal(struct drm_i915_gem_request *signaller_req,
>  			   unsigned int num_dwords)
>  {
>  #define MBOX_UPDATE_DWORDS 6
> +	struct intel_engine_cs *signaller = signaller_req->ring;
>  	struct drm_device *dev = signaller->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *waiter;
> @@ -952,7 +962,7 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
>  	num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS;
>  #undef MBOX_UPDATE_DWORDS
>  
> -	ret = intel_ring_begin(signaller, num_dwords);
> +	ret = intel_ring_begin(signaller_req, num_dwords);
>  	if (ret)
>  		return ret;
>  
> @@ -962,8 +972,7 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
>  		if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
>  			continue;
>  
> -		seqno = i915_gem_request_get_seqno(
> -					   signaller->outstanding_lazy_request);
> +		seqno = i915_gem_request_get_seqno(signaller_req);
>  		intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
>  					   MI_FLUSH_DW_OP_STOREDW);
>  		intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
> @@ -978,9 +987,10 @@ static int gen8_xcs_signal(struct intel_engine_cs *signaller,
>  	return 0;
>  }
>  
> -static int gen6_signal(struct intel_engine_cs *signaller,
> +static int gen6_signal(struct drm_i915_gem_request *signaller_req,
>  		       unsigned int num_dwords)
>  {
> +	struct intel_engine_cs *signaller = signaller_req->ring;
>  	struct drm_device *dev = signaller->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct intel_engine_cs *useless;
> @@ -991,15 +1001,14 @@ static int gen6_signal(struct intel_engine_cs *signaller,
>  	num_dwords += round_up((num_rings-1) * MBOX_UPDATE_DWORDS, 2);
>  #undef MBOX_UPDATE_DWORDS
>  
> -	ret = intel_ring_begin(signaller, num_dwords);
> +	ret = intel_ring_begin(signaller_req, num_dwords);
>  	if (ret)
>  		return ret;
>  
>  	for_each_ring(useless, dev_priv, i) {
>  		u32 mbox_reg = signaller->semaphore.mbox.signal[i];
>  		if (mbox_reg != GEN6_NOSYNC) {
> -			u32 seqno = i915_gem_request_get_seqno(
> -					   signaller->outstanding_lazy_request);
> +			u32 seqno = i915_gem_request_get_seqno(signaller_req);
>  			intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
>  			intel_ring_emit(signaller, mbox_reg);
>  			intel_ring_emit(signaller, seqno);
> @@ -1016,29 +1025,28 @@ static int gen6_signal(struct intel_engine_cs *signaller,
>  /**
>   * gen6_add_request - Update the semaphore mailbox registers
>   *
> - * @ring - ring that is adding a request
> - * @seqno - return seqno stuck into the ring
> + * @request - request to write to the ring
>   *
>   * Update the mailbox registers in the *other* rings with the current seqno.
>   * This acts like a signal in the canonical semaphore.
>   */
>  static int
> -gen6_add_request(struct intel_engine_cs *ring)
> +gen6_add_request(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	if (ring->semaphore.signal)
> -		ret = ring->semaphore.signal(ring, 4);
> +		ret = ring->semaphore.signal(req, 4);
>  	else
> -		ret = intel_ring_begin(ring, 4);
> +		ret = intel_ring_begin(req, 4);
>  
>  	if (ret)
>  		return ret;
>  
>  	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
>  	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
> -	intel_ring_emit(ring,
> -		    i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> +	intel_ring_emit(ring, i915_gem_request_get_seqno(req));
>  	intel_ring_emit(ring, MI_USER_INTERRUPT);
>  	__intel_ring_advance(ring);
>  
> @@ -1061,14 +1069,15 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
>   */
>  
>  static int
> -gen8_ring_sync(struct intel_engine_cs *waiter,
> +gen8_ring_sync(struct drm_i915_gem_request *waiter_req,
>  	       struct intel_engine_cs *signaller,
>  	       u32 seqno)
>  {
> +	struct intel_engine_cs *waiter = waiter_req->ring;
>  	struct drm_i915_private *dev_priv = waiter->dev->dev_private;
>  	int ret;
>  
> -	ret = intel_ring_begin(waiter, 4);
> +	ret = intel_ring_begin(waiter_req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -1086,10 +1095,11 @@ gen8_ring_sync(struct intel_engine_cs *waiter,
>  }
>  
>  static int
> -gen6_ring_sync(struct intel_engine_cs *waiter,
> +gen6_ring_sync(struct drm_i915_gem_request *waiter_req,
>  	       struct intel_engine_cs *signaller,
>  	       u32 seqno)
>  {
> +	struct intel_engine_cs *waiter = waiter_req->ring;
>  	u32 dw1 = MI_SEMAPHORE_MBOX |
>  		  MI_SEMAPHORE_COMPARE |
>  		  MI_SEMAPHORE_REGISTER;
> @@ -1104,7 +1114,7 @@ gen6_ring_sync(struct intel_engine_cs *waiter,
>  
>  	WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
>  
> -	ret = intel_ring_begin(waiter, 4);
> +	ret = intel_ring_begin(waiter_req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -1135,8 +1145,9 @@ do {									\
>  } while (0)
>  
>  static int
> -pc_render_add_request(struct intel_engine_cs *ring)
> +pc_render_add_request(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
>  	int ret;
>  
> @@ -1148,7 +1159,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
>  	 * incoherence by flushing the 6 PIPE_NOTIFY buffers out to
>  	 * memory before requesting an interrupt.
>  	 */
> -	ret = intel_ring_begin(ring, 32);
> +	ret = intel_ring_begin(req, 32);
>  	if (ret)
>  		return ret;
>  
> @@ -1156,8 +1167,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
>  			PIPE_CONTROL_WRITE_FLUSH |
>  			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
>  	intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
> -	intel_ring_emit(ring,
> -		    i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> +	intel_ring_emit(ring, i915_gem_request_get_seqno(req));
>  	intel_ring_emit(ring, 0);
>  	PIPE_CONTROL_FLUSH(ring, scratch_addr);
>  	scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
> @@ -1176,8 +1186,7 @@ pc_render_add_request(struct intel_engine_cs *ring)
>  			PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
>  			PIPE_CONTROL_NOTIFY);
>  	intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
> -	intel_ring_emit(ring,
> -		    i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> +	intel_ring_emit(ring, i915_gem_request_get_seqno(req));
>  	intel_ring_emit(ring, 0);
>  	__intel_ring_advance(ring);
>  
> @@ -1390,13 +1399,14 @@ void intel_ring_setup_status_page(struct intel_engine_cs *ring)
>  }
>  
>  static int
> -bsd_ring_flush(struct intel_engine_cs *ring,
> +bsd_ring_flush(struct drm_i915_gem_request *req,
>  	       u32     invalidate_domains,
>  	       u32     flush_domains)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -1407,18 +1417,18 @@ bsd_ring_flush(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -i9xx_add_request(struct intel_engine_cs *ring)
> +i9xx_add_request(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
>  	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
>  	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
> -	intel_ring_emit(ring,
> -		    i915_gem_request_get_seqno(ring->outstanding_lazy_request));
> +	intel_ring_emit(ring, i915_gem_request_get_seqno(req));
>  	intel_ring_emit(ring, MI_USER_INTERRUPT);
>  	__intel_ring_advance(ring);
>  
> @@ -1550,13 +1560,14 @@ gen8_ring_put_irq(struct intel_engine_cs *ring)
>  }
>  
>  static int
> -i965_dispatch_execbuffer(struct intel_engine_cs *ring,
> +i965_dispatch_execbuffer(struct drm_i915_gem_request *req,
>  			 u64 offset, u32 length,
>  			 unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -1575,14 +1586,15 @@ i965_dispatch_execbuffer(struct intel_engine_cs *ring,
>  #define I830_TLB_ENTRIES (2)
>  #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT)
>  static int
> -i830_dispatch_execbuffer(struct intel_engine_cs *ring,
> -				u64 offset, u32 len,
> -				unsigned flags)
> +i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
> +			 u64 offset, u32 len,
> +			 unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	u32 cs_offset = ring->scratch.gtt_offset;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 6);
> +	ret = intel_ring_begin(req, 6);
>  	if (ret)
>  		return ret;
>  
> @@ -1599,7 +1611,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
>  		if (len > I830_BATCH_LIMIT)
>  			return -ENOSPC;
>  
> -		ret = intel_ring_begin(ring, 6 + 2);
> +		ret = intel_ring_begin(req, 6 + 2);
>  		if (ret)
>  			return ret;
>  
> @@ -1622,7 +1634,7 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
>  		offset = cs_offset;
>  	}
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -1636,13 +1648,14 @@ i830_dispatch_execbuffer(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -i915_dispatch_execbuffer(struct intel_engine_cs *ring,
> +i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
>  			 u64 offset, u32 len,
>  			 unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -1885,6 +1898,7 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
>  
>  	intel_unpin_ringbuffer_obj(ringbuf);
>  	intel_destroy_ringbuffer_obj(ringbuf);
> +	WARN_ON(ring->outstanding_lazy_request);
>  	i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
>  
>  	if (ring->cleanup)
> @@ -2007,8 +2021,9 @@ int intel_ring_idle(struct intel_engine_cs *ring)
>  	int ret;
>  
>  	/* We need to add any requests required to flush the objects and ring */
> +	WARN_ON(ring->outstanding_lazy_request);
>  	if (ring->outstanding_lazy_request) {
> -		ret = i915_add_request(ring);
> +		ret = i915_add_request(ring->outstanding_lazy_request);
>  		if (ret)
>  			return ret;
>  	}
> @@ -2025,13 +2040,18 @@ int intel_ring_idle(struct intel_engine_cs *ring)
>  }
>  
>  int
> -intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
> +intel_ring_alloc_request(struct intel_engine_cs *ring,
> +			 struct intel_context *ctx,
> +			 struct drm_i915_gem_request **req_out)
>  {
>  	int ret;
>  	struct drm_i915_gem_request *request;
>  	struct drm_i915_private *dev_private = ring->dev->dev_private;
>  
> -	if (ring->outstanding_lazy_request)
> +	if (!req_out)
> +		return -EINVAL;
> +
> +	if ((*req_out = ring->outstanding_lazy_request) != NULL)
>  		return 0;
>  
>  	request = kzalloc(sizeof(*request), GFP_KERNEL);
> @@ -2053,7 +2073,7 @@ intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx
>  	spewThisReq(request, "\x1B[32mCreated: %d:%d, ref => %d\x1B[0m", request->uniq, request->seqno, request->ref.refcount.counter);
>  
>  	//printk(KERN_INFO "%s:%d> <%s> OLR = 0x%p, uniq = %d, seqno = %d\n", __func__, __LINE__, ring->name, request, request->uniq, request->seqno);
> -	ring->outstanding_lazy_request = request;
> +	*req_out = ring->outstanding_lazy_request = request;
>  	return 0;
>  }
>  
> @@ -2078,9 +2098,10 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring,
>  	return 0;
>  }
>  
> -int intel_ring_begin(struct intel_engine_cs *ring,
> +int intel_ring_begin(struct drm_i915_gem_request *req,
>  		     int num_dwords)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_i915_private *dev_priv = ring->dev->dev_private;
>  	int ret;
>  
> @@ -2093,18 +2114,14 @@ int intel_ring_begin(struct intel_engine_cs *ring,
>  	if (ret)
>  		return ret;
>  
> -	/* Preallocate the olr before touching the ring */
> -	ret = intel_ring_alloc_request(ring, NULL);
> -	if (ret)
> -		return ret;
> -
>  	ring->buffer->space -= num_dwords * sizeof(uint32_t);
>  	return 0;
>  }
>  
>  /* Align the ring tail to a cacheline boundary */
> -int intel_ring_cacheline_align(struct intel_engine_cs *ring)
> +int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
>  	int ret;
>  
> @@ -2112,7 +2129,7 @@ int intel_ring_cacheline_align(struct intel_engine_cs *ring)
>  		return 0;
>  
>  	num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
> -	ret = intel_ring_begin(ring, num_dwords);
> +	ret = intel_ring_begin(req, num_dwords);
>  	if (ret)
>  		return ret;
>  
> @@ -2176,13 +2193,14 @@ static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring,
>  		   _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
>  }
>  
> -static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
> +static int gen6_bsd_ring_flush(struct drm_i915_gem_request *req,
>  			       u32 invalidate, u32 flush)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	uint32_t cmd;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -2212,14 +2230,15 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +gen8_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
>  			      u64 offset, u32 len,
>  			      unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	bool ppgtt = USES_PPGTT(ring->dev) && !(flags & I915_DISPATCH_SECURE);
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -2234,13 +2253,14 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +hsw_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
>  			      u64 offset, u32 len,
>  			      unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -2256,13 +2276,14 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>  }
>  
>  static int
> -gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
> +gen6_ring_dispatch_execbuffer(struct drm_i915_gem_request *req,
>  			      u64 offset, u32 len,
>  			      unsigned flags)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 2);
> +	ret = intel_ring_begin(req, 2);
>  	if (ret)
>  		return ret;
>  
> @@ -2278,15 +2299,16 @@ gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
>  
>  /* Blitter support (SandyBridge+) */
>  
> -static int gen6_ring_flush(struct intel_engine_cs *ring,
> +static int gen6_ring_flush(struct drm_i915_gem_request *req,
>  			   u32 invalidate, u32 flush)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	struct drm_device *dev = ring->dev;
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	uint32_t cmd;
>  	int ret;
>  
> -	ret = intel_ring_begin(ring, 4);
> +	ret = intel_ring_begin(req, 4);
>  	if (ret)
>  		return ret;
>  
> @@ -2315,7 +2337,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
>  
>  	if (!invalidate && flush) {
>  		if (IS_GEN7(dev))
> -			return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
> +			return gen7_ring_fbc_flush(req, FBC_REND_CACHE_CLEAN);
>  		else if (IS_BROADWELL(dev))
>  			dev_priv->fbc.need_sw_cache_clean = true;
>  	}
> @@ -2696,14 +2718,15 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
>  }
>  
>  int
> -intel_ring_flush_all_caches(struct intel_engine_cs *ring)
> +intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	int ret;
>  
>  	if (!ring->gpu_caches_dirty)
>  		return 0;
>  
> -	ret = ring->flush(ring, 0, I915_GEM_GPU_DOMAINS);
> +	ret = ring->flush(req, 0, I915_GEM_GPU_DOMAINS);
>  	if (ret)
>  		return ret;
>  
> @@ -2714,8 +2737,9 @@ intel_ring_flush_all_caches(struct intel_engine_cs *ring)
>  }
>  
>  int
> -intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
> +intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
>  {
> +	struct intel_engine_cs *ring = req->ring;
>  	uint32_t flush_domains;
>  	int ret;
>  
> @@ -2723,7 +2747,7 @@ intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
>  	if (ring->gpu_caches_dirty)
>  		flush_domains = I915_GEM_GPU_DOMAINS;
>  
> -	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, flush_domains);
> +	ret = ring->flush(req, I915_GEM_GPU_DOMAINS, flush_domains);
>  	if (ret)
>  		return ret;
>  
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 48cbb00..a7e47ad 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -154,15 +154,15 @@ struct  intel_engine_cs {
>  
>  	int		(*init_hw)(struct intel_engine_cs *ring);
>  
> -	int		(*init_context)(struct intel_engine_cs *ring,
> +	int		(*init_context)(struct drm_i915_gem_request *req,
>  					struct intel_context *ctx);
>  
>  	void		(*write_tail)(struct intel_engine_cs *ring,
>  				      u32 value);
> -	int __must_check (*flush)(struct intel_engine_cs *ring,
> +	int __must_check (*flush)(struct drm_i915_gem_request *req,
>  				  u32	invalidate_domains,
>  				  u32	flush_domains);
> -	int		(*add_request)(struct intel_engine_cs *ring);
> +	int		(*add_request)(struct drm_i915_gem_request *req);
>  	/* Some chipsets are not quite as coherent as advertised and need
>  	 * an expensive kick to force a true read of the up-to-date seqno.
>  	 * However, the up-to-date seqno is not always required and the last
> @@ -173,7 +173,7 @@ struct  intel_engine_cs {
>  				     bool lazy_coherency);
>  	void		(*set_seqno)(struct intel_engine_cs *ring,
>  				     u32 seqno);
> -	int		(*dispatch_execbuffer)(struct intel_engine_cs *ring,
> +	int		(*dispatch_execbuffer)(struct drm_i915_gem_request *req,
>  					       u64 offset, u32 length,
>  					       unsigned dispatch_flags);
>  #define I915_DISPATCH_SECURE 0x1
> @@ -231,10 +231,10 @@ struct  intel_engine_cs {
>  		};
>  
>  		/* AKA wait() */
> -		int	(*sync_to)(struct intel_engine_cs *ring,
> -				   struct intel_engine_cs *to,
> +		int	(*sync_to)(struct drm_i915_gem_request *to_req,
> +				   struct intel_engine_cs *from,
>  				   u32 seqno);
> -		int	(*signal)(struct intel_engine_cs *signaller,
> +		int	(*signal)(struct drm_i915_gem_request *signaller_req,
>  				  /* num_dwords needed by caller */
>  				  unsigned int num_dwords);
>  	} semaphore;
> @@ -245,11 +245,11 @@ struct  intel_engine_cs {
>  	struct list_head execlist_retired_req_list;
>  	u8 next_context_status_buffer;
>  	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
> -	int		(*emit_request)(struct intel_ringbuffer *ringbuf);
> -	int		(*emit_flush)(struct intel_ringbuffer *ringbuf,
> +	int		(*emit_request)(struct drm_i915_gem_request *req);
> +	int		(*emit_flush)(struct drm_i915_gem_request *req,
>  				      u32 invalidate_domains,
>  				      u32 flush_domains);
> -	int		(*emit_bb_start)(struct intel_ringbuffer *ringbuf,
> +	int		(*emit_bb_start)(struct drm_i915_gem_request *req,
>  					 u64 offset, unsigned flags);
>  
>  	/**
> @@ -433,10 +433,11 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev,
>  void intel_stop_ring_buffer(struct intel_engine_cs *ring);
>  void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
>  
> -int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
> -int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
> +int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
> +int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
>  int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
> -					  struct intel_context *ctx);
> +					  struct intel_context *ctx,
> +					  struct drm_i915_gem_request **req_out);
>  static inline void intel_ring_emit(struct intel_engine_cs *ring,
>  				   u32 data)
>  {
> @@ -457,8 +458,8 @@ void __intel_ring_advance(struct intel_engine_cs *ring);
>  
>  int __must_check intel_ring_idle(struct intel_engine_cs *ring);
>  void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
> -int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
> -int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
> +int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
> +int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
>  
>  void intel_fini_pipe_control(struct intel_engine_cs *ring);
>  int intel_init_pipe_control(struct intel_engine_cs *ring);
> @@ -479,11 +480,4 @@ static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
>  	return ringbuf->tail;
>  }
>  
> -static inline struct drm_i915_gem_request *
> -intel_ring_get_request(struct intel_engine_cs *ring)
> -{
> -	BUG_ON(ring->outstanding_lazy_request == NULL);
> -	return ring->outstanding_lazy_request;
> -}
> -
>  #endif /* _INTEL_RINGBUFFER_H_ */
> -- 
> 1.7.9.5
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch


More information about the Intel-gfx mailing list