Commit 7ba717cf authored by Thomas Daniel's avatar Thomas Daniel Committed by Daniel Vetter
Browse files

drm/i915/bdw: Pin the ringbuffer backing object to GGTT on-demand 



Same as with the context, pinning to GGTT regardless is harmful (it
badly fragments the GGTT and can even exhaust it).

Unfortunately, this case is also more complex than the previous one
because we need to map and access the ringbuffer in several places
along the execbuffer path (and we cannot make do by leaving the
default ringbuffer pinned, as before). Also, the context object
itself contains a pointer to the ringbuffer address that we have to
keep updated if we are going to allow the ringbuffer to move around.

v2: Same as with the context pinning, we cannot really do it during
an interrupt. Also, pin the default ringbuffers objects regardless
(makes error capture a lot easier).

v3: Rebased. Take a pin reference of the ringbuffer for each item
in the execlist request queue because the hardware may still be using
the ringbuffer after the MI_USER_INTERRUPT to notify the seqno update
is executed.  The ringbuffer must remain pinned until the context save
is complete.  No longer pin and unpin ringbuffer in
populate_lr_context() - this transient address is meaningless and the
pinning can cause a sleep while atomic.

v4: Moved ringbuffer pin and unpin into the lr_context_pin functions.
Downgraded pinning check BUG_ONs to WARN_ONs.

v5: Reinstated WARN_ONs for unexpected execlist states.  Removed unused
variable.

Issue: VIZ-4277
Signed-off-by: default avatarOscar Mateo <oscar.mateo@intel.com>
Signed-off-by: default avatarThomas Daniel <thomas.daniel@intel.com>
Reviewed-by: default avatarAkash Goel <akash.goels@gmail.com>
Reviewed-by: default avatarDeepak <S&lt;deepak.s@linux.intel.com>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
parent dcb4c12a

drivers/gpu/drm/i915/intel_lrc.c

+75 −27
Original line number Diff line number Diff line
@@ -203,6 +203,9 @@ enum { 
};

#define GEN8_CTX_ID_SHIFT 32



static int intel_lr_context_pin(struct intel_engine_cs *ring,

		struct intel_context *ctx);



/**

 * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists

 * @dev: DRM device.
@@ -354,7 +357,9 @@ static void execlists_elsp_write(struct intel_engine_cs *ring, 
	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);

}



static int execlists_ctx_write_tail(struct drm_i915_gem_object *ctx_obj, u32 tail)

static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,

				    struct drm_i915_gem_object *ring_obj,

				    u32 tail)

{

	struct page *page;

	uint32_t *reg_state;
@@ -363,6 +368,7 @@ static int execlists_ctx_write_tail(struct drm_i915_gem_object *ctx_obj, u32 tai 
	reg_state = kmap_atomic(page);



	reg_state[CTX_RING_TAIL+1] = tail;

	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);



	kunmap_atomic(reg_state);
@@ -373,21 +379,25 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring, 
				      struct intel_context *to0, u32 tail0,

				      struct intel_context *to1, u32 tail1)

{

	struct drm_i915_gem_object *ctx_obj0;

	struct drm_i915_gem_object *ctx_obj0 = to0->engine[ring->id].state;

	struct intel_ringbuffer *ringbuf0 = to0->engine[ring->id].ringbuf;

	struct drm_i915_gem_object *ctx_obj1 = NULL;

	struct intel_ringbuffer *ringbuf1 = NULL;



	ctx_obj0 = to0->engine[ring->id].state;

	BUG_ON(!ctx_obj0);

	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));

	WARN_ON(!i915_gem_obj_is_pinned(ringbuf0->obj));



	execlists_ctx_write_tail(ctx_obj0, tail0);

	execlists_update_context(ctx_obj0, ringbuf0->obj, tail0);



	if (to1) {

		ringbuf1 = to1->engine[ring->id].ringbuf;

		ctx_obj1 = to1->engine[ring->id].state;

		BUG_ON(!ctx_obj1);

		WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));

		WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));



		execlists_ctx_write_tail(ctx_obj1, tail1);

		execlists_update_context(ctx_obj1, ringbuf1->obj, tail1);

	}



	execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
@@ -537,6 +547,10 @@ static int execlists_context_queue(struct intel_engine_cs *ring, 
		return -ENOMEM;

	req->ctx = to;

	i915_gem_context_reference(req->ctx);



	if (to != ring->default_context)

		intel_lr_context_pin(ring, to);



	req->ring = ring;

	req->tail = tail;
@@ -745,6 +759,12 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring) 
	spin_unlock_irqrestore(&ring->execlist_lock, flags);



	list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {

		struct intel_context *ctx = req->ctx;

		struct drm_i915_gem_object *ctx_obj =

				ctx->engine[ring->id].state;



		if (ctx_obj && (ctx != ring->default_context))

			intel_lr_context_unpin(ring, ctx);

		intel_runtime_pm_put(dev_priv);

		i915_gem_context_unreference(req->ctx);

		list_del(&req->execlist_link);
@@ -816,6 +836,7 @@ static int intel_lr_context_pin(struct intel_engine_cs *ring, 
		struct intel_context *ctx)

{

	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;

	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;

	int ret = 0;



	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
@@ -823,9 +844,20 @@ static int intel_lr_context_pin(struct intel_engine_cs *ring, 
		ret = i915_gem_obj_ggtt_pin(ctx_obj,

				GEN8_LR_CONTEXT_ALIGN, 0);

		if (ret)

			ctx->engine[ring->id].unpin_count = 0;

			goto reset_unpin_count;



		ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);

		if (ret)

			goto unpin_ctx_obj;

	}



	return ret;



unpin_ctx_obj:

	i915_gem_object_ggtt_unpin(ctx_obj);

reset_unpin_count:

	ctx->engine[ring->id].unpin_count = 0;



	return ret;

}
@@ -833,13 +865,16 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring, 
		struct intel_context *ctx)

{

	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;

	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;



	if (ctx_obj) {

		WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));

		if (--ctx->engine[ring->id].unpin_count == 0)

		if (--ctx->engine[ring->id].unpin_count == 0) {

			intel_unpin_ringbuffer_obj(ringbuf);

			i915_gem_object_ggtt_unpin(ctx_obj);

		}

	}

}



static int logical_ring_alloc_seqno(struct intel_engine_cs *ring,

				    struct intel_context *ctx)
@@ -1595,7 +1630,6 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o 
{

	struct drm_device *dev = ring->dev;

	struct drm_i915_private *dev_priv = dev->dev_private;

	struct drm_i915_gem_object *ring_obj = ringbuf->obj;

	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;

	struct page *page;

	uint32_t *reg_state;
@@ -1641,7 +1675,9 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o 
	reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);

	reg_state[CTX_RING_TAIL+1] = 0;

	reg_state[CTX_RING_BUFFER_START] = RING_START(ring->mmio_base);

	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);

	/* Ring buffer start address is not known until the buffer is pinned.

	 * It is written to the context image in execlists_update_context()

	 */

	reg_state[CTX_RING_BUFFER_CONTROL] = RING_CTL(ring->mmio_base);

	reg_state[CTX_RING_BUFFER_CONTROL+1] =

			((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID;
@@ -1723,10 +1759,12 @@ void intel_lr_context_free(struct intel_context *ctx) 
					ctx->engine[i].ringbuf;

			struct intel_engine_cs *ring = ringbuf->ring;



			if (ctx == ring->default_context) {

				intel_unpin_ringbuffer_obj(ringbuf);

				i915_gem_object_ggtt_unpin(ctx_obj);

			}

			intel_destroy_ringbuffer_obj(ringbuf);

			kfree(ringbuf);

			if (ctx == ring->default_context)

				i915_gem_object_ggtt_unpin(ctx_obj);

			drm_gem_object_unreference(&ctx_obj->base);

		}

	}
@@ -1823,11 +1861,8 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 
	if (!ringbuf) {

		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",

				ring->name);

		if (is_global_default_ctx)

			i915_gem_object_ggtt_unpin(ctx_obj);

		drm_gem_object_unreference(&ctx_obj->base);

		ret = -ENOMEM;

		return ret;

		goto error_unpin_ctx;

	}



	ringbuf->ring = ring;
@@ -1840,22 +1875,30 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 
	ringbuf->space = ringbuf->size;

	ringbuf->last_retired_head = -1;



	/* TODO: For now we put this in the mappable region so that we can reuse

	 * the existing ringbuffer code which ioremaps it. When we start

	 * creating many contexts, this will no longer work and we must switch

	 * to a kmapish interface.

	 */

	if (ringbuf->obj == NULL) {

		ret = intel_alloc_ringbuffer_obj(dev, ringbuf);

		if (ret) {

		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer obj %s: %d\n",

			DRM_DEBUG_DRIVER(

				"Failed to allocate ringbuffer obj %s: %d\n",

				ring->name, ret);

		goto error;

			goto error_free_rbuf;

		}



		if (is_global_default_ctx) {

			ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);

			if (ret) {

				DRM_ERROR(

					"Failed to pin and map ringbuffer %s: %d\n",

					ring->name, ret);

				goto error_destroy_rbuf;

			}

		}



	}



	ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf);

	if (ret) {

		DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);

		intel_destroy_ringbuffer_obj(ringbuf);

		goto error;

	}
@@ -1877,7 +1920,6 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 
			DRM_ERROR("Init render state failed: %d\n", ret);

			ctx->engine[ring->id].ringbuf = NULL;

			ctx->engine[ring->id].state = NULL;

			intel_destroy_ringbuffer_obj(ringbuf);

			goto error;

		}

		ctx->rcs_initialized = true;
@@ -1886,7 +1928,13 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 
	return 0;



error:

	if (is_global_default_ctx)

		intel_unpin_ringbuffer_obj(ringbuf);

error_destroy_rbuf:

	intel_destroy_ringbuffer_obj(ringbuf);

error_free_rbuf:

	kfree(ringbuf);

error_unpin_ctx:

	if (is_global_default_ctx)

		i915_gem_object_ggtt_unpin(ctx_obj);

	drm_gem_object_unreference(&ctx_obj->base);

drivers/gpu/drm/i915/intel_ringbuffer.c

+50 −35
Original line number Diff line number Diff line
@@ -1722,26 +1722,50 @@ static int init_phys_status_page(struct intel_engine_cs *ring) 
	return 0;

}



void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)

void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)

{

	if (!ringbuf->obj)

		return;



	iounmap(ringbuf->virtual_start);

	ringbuf->virtual_start = NULL;

	i915_gem_object_ggtt_unpin(ringbuf->obj);

	drm_gem_object_unreference(&ringbuf->obj->base);

	ringbuf->obj = NULL;

}



int intel_alloc_ringbuffer_obj(struct drm_device *dev,

int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,

				     struct intel_ringbuffer *ringbuf)

{

	struct drm_i915_private *dev_priv = to_i915(dev);

	struct drm_i915_gem_object *obj;

	struct drm_i915_gem_object *obj = ringbuf->obj;

	int ret;



	if (ringbuf->obj)

	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);

	if (ret)

		return ret;



	ret = i915_gem_object_set_to_gtt_domain(obj, true);

	if (ret) {

		i915_gem_object_ggtt_unpin(obj);

		return ret;

	}



	ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +

			i915_gem_obj_ggtt_offset(obj), ringbuf->size);

	if (ringbuf->virtual_start == NULL) {

		i915_gem_object_ggtt_unpin(obj);

		return -EINVAL;

	}



	return 0;

}



void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)

{

	drm_gem_object_unreference(&ringbuf->obj->base);

	ringbuf->obj = NULL;

}



int intel_alloc_ringbuffer_obj(struct drm_device *dev,

			       struct intel_ringbuffer *ringbuf)

{

	struct drm_i915_gem_object *obj;



	obj = NULL;

	if (!HAS_LLC(dev))
@@ -1754,30 +1778,9 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev, 
	/* mark ring buffers as read-only from GPU side by default */

	obj->gt_ro = 1;



	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);

	if (ret)

		goto err_unref;



	ret = i915_gem_object_set_to_gtt_domain(obj, true);

	if (ret)

		goto err_unpin;



	ringbuf->virtual_start =

		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),

				ringbuf->size);

	if (ringbuf->virtual_start == NULL) {

		ret = -EINVAL;

		goto err_unpin;

	}



	ringbuf->obj = obj;

	return 0;



err_unpin:

	i915_gem_object_ggtt_unpin(obj);

err_unref:

	drm_gem_object_unreference(&obj->base);

	return ret;

	return 0;

}



static int intel_init_ring_buffer(struct drm_device *dev,
@@ -1814,12 +1817,23 @@ static int intel_init_ring_buffer(struct drm_device *dev, 
			goto error;

	}



	if (ringbuf->obj == NULL) {

		ret = intel_alloc_ringbuffer_obj(dev, ringbuf);

		if (ret) {

		DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret);

			DRM_ERROR("Failed to allocate ringbuffer %s: %d\n",

					ring->name, ret);

			goto error;

		}



		ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);

		if (ret) {

			DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",

					ring->name, ret);

			intel_destroy_ringbuffer_obj(ringbuf);

			goto error;

		}

	}



	/* Workaround an erratum on the i830 which causes a hang if

	 * the TAIL pointer points to within the last 2 cachelines

	 * of the buffer.
@@ -1858,6 +1872,7 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) 
	intel_stop_ring_buffer(ring);

	WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0);



	intel_unpin_ringbuffer_obj(ringbuf);

	intel_destroy_ringbuffer_obj(ringbuf);

	ring->preallocated_lazy_request = NULL;

	ring->outstanding_lazy_seqno = 0;

drivers/gpu/drm/i915/intel_ringbuffer.h

+3 −0
Original line number Diff line number Diff line
@@ -383,6 +383,9 @@ intel_write_status_page(struct intel_engine_cs *ring, 
#define I915_GEM_HWS_SCRATCH_INDEX	0x30

#define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)



void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);

int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,

				     struct intel_ringbuffer *ringbuf);

void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf);

int intel_alloc_ringbuffer_obj(struct drm_device *dev,

			       struct intel_ringbuffer *ringbuf);

CRA Git | Maintained and supported by SUSTech CRA and CCSE