cregit-Linux how code gets into the kernel

Release 4.11 drivers/gpu/drm/i915/i915_gem_render_state.c

Directory: drivers/gpu/drm/i915
/*
 * Copyright © 2014 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Mika Kuoppala <mika.kuoppala@intel.com>
 *
 */

#include "i915_drv.h"
#include "intel_renderstate.h"


struct intel_render_state {
	
const struct intel_renderstate_rodata *rodata;
	
struct i915_vma *vma;
	
u32 batch_offset;
	
u32 batch_size;
	
u32 aux_offset;
	
u32 aux_size;
};



static const struct intel_renderstate_rodata *

render_state_get_rodata(const struct intel_engine_cs *engine)
{
	switch (INTEL_GEN(engine->i915)) {
	case 6:
		return &gen6_null_state;
	case 7:
		return &gen7_null_state;
	case 8:
		return &gen8_null_state;
	case 9:
		return &gen9_null_state;
	}

	return NULL;
}


Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson4477.19%360.00%


Armin Reese712.28%120.00%


Mika Kuoppala610.53%120.00%


Total57100.00%5100.00%



/*
 * Macro to add commands to auxiliary batch.
 * This macro only checks for page overflow before inserting the commands,
 * this is sufficient as the null state generator makes the final batch
 * with two passes to build command and state separately. At this point
 * the size of both are known and it compacts them by relocating the state
 * right after the commands taking care of alignment so we should sufficient
 * space below them for adding new commands.
 */

#define OUT_BATCH(batch, i, val)				\
	do {                                                    \
                if ((i) >= PAGE_SIZE / sizeof(u32))             \
                        goto err;                               \
                (batch)[(i)++] = (val);                         \
        } while(0)




static int render_state_setup(struct intel_render_state *so,
			      struct drm_i915_private *i915)
{
	const struct intel_renderstate_rodata *rodata = so->rodata;
	struct drm_i915_gem_object *obj = so->vma->obj;
	unsigned int i = 0, reloc_index = 0;
	unsigned int needs_clflush;
	u32 *d;
	int ret;

	ret = i915_gem_obj_prepare_shmem_write(obj, &needs_clflush);
	if (ret)
		return ret;

	d = kmap_atomic(i915_gem_object_get_dirty_page(obj, 0));

	while (i < rodata->batch_items) {
		u32 s = rodata->batch[i];

		if (i * 4  == rodata->reloc[reloc_index]) {
			u64 r = s + so->vma->node.start;
			s = lower_32_bits(r);
			if (HAS_64BIT_RELOC(i915)) {
				if (i + 1 >= rodata->batch_items ||
				    rodata->batch[i + 1] != 0)
					goto err;

				d[i++] = s;
				s = upper_32_bits(r);
			}

			reloc_index++;
		}

		d[i++] = s;
	}

	if (rodata->reloc[reloc_index] != -1) {
		DRM_ERROR("only %d relocs resolved\n", reloc_index);
		goto err;
	}

	so->batch_offset = so->vma->node.start;
	so->batch_size = rodata->batch_items * sizeof(u32);

	while (i % CACHELINE_DWORDS)
		OUT_BATCH(d, i, MI_NOOP);

	so->aux_offset = i * sizeof(u32);

	if (HAS_POOLED_EU(i915)) {
		/*
                 * We always program 3x6 pool config but depending upon which
                 * subslice is disabled HW drops down to appropriate config
                 * shown below.
                 *
                 * In the below table 2x6 config always refers to
                 * fused-down version, native 2x6 is not available and can
                 * be ignored
                 *
                 * SNo  subslices config                eu pool configuration
                 * -----------------------------------------------------------
                 * 1    3 subslices enabled (3x6)  -    0x00777000  (9+9)
                 * 2    ss0 disabled (2x6)         -    0x00777000  (3+9)
                 * 3    ss1 disabled (2x6)         -    0x00770000  (6+6)
                 * 4    ss2 disabled (2x6)         -    0x00007000  (9+3)
                 */
		u32 eu_pool_config = 0x00777000;

		OUT_BATCH(d, i, GEN9_MEDIA_POOL_STATE);
		OUT_BATCH(d, i, GEN9_MEDIA_POOL_ENABLE);
		OUT_BATCH(d, i, eu_pool_config);
		OUT_BATCH(d, i, 0);
		OUT_BATCH(d, i, 0);
		OUT_BATCH(d, i, 0);
	}

	OUT_BATCH(d, i, MI_BATCH_BUFFER_END);
	so->aux_size = i * sizeof(u32) - so->aux_offset;
	so->aux_offset += so->batch_offset;
	/*
         * Since we are sending length, we need to strictly conform to
         * all requirements. For Gen2 this must be a multiple of 8.
         */
	so->aux_size = ALIGN(so->aux_size, 8);

	if (needs_clflush)
		drm_clflush_virt_range(d, i * sizeof(u32));
	kunmap_atomic(d);

	ret = i915_gem_object_set_to_gtt_domain(obj, false);
out:
	i915_gem_obj_finish_shmem_access(obj);
	return ret;

err:
	kunmap_atomic(d);
	ret = -EINVAL;
	goto out;
}


Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson16737.44%330.00%


Mika Kuoppala14231.84%220.00%


Arun Siluvery12928.92%220.00%


Joonas Lahtinen40.90%110.00%


Dave Gordon30.67%110.00%


Tvrtko A. Ursulin10.22%110.00%


Total446100.00%10100.00%




#undef OUT_BATCH




int i915_gem_render_state_init(struct intel_engine_cs *engine)
{
	struct intel_render_state *so;
	const struct intel_renderstate_rodata *rodata;
	struct drm_i915_gem_object *obj;
	int ret;

	if (engine->id != RCS)
		return 0;

	rodata = render_state_get_rodata(engine);
	if (!rodata)
		return 0;

	if (rodata->batch_items * 4 > PAGE_SIZE)
		return -EINVAL;

	so = kmalloc(sizeof(*so), GFP_KERNEL);
	if (!so)
		return -ENOMEM;

	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
	if (IS_ERR(obj)) {
		ret = PTR_ERR(obj);
		goto err_free;
	}

	so->vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
	if (IS_ERR(so->vma)) {
		ret = PTR_ERR(so->vma);
		goto err_obj;
	}

	so->rodata = rodata;
	engine->render_state = so;
	return 0;

err_obj:
	i915_gem_object_put(obj);
err_free:
	kfree(so);
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson15478.57%763.64%


Mika Kuoppala3115.82%218.18%


Oscar Mateo105.10%19.09%


Tvrtko A. Ursulin10.51%19.09%


Total196100.00%11100.00%






int i915_gem_render_state_emit(struct drm_i915_gem_request *req)
{
	struct intel_render_state *so;
	int ret;

	lockdep_assert_held(&req->i915->drm.struct_mutex);

	so = req->engine->render_state;
	if (!so)
		return 0;

	/* Recreate the page after shrinking */
	if (!so->vma->obj->mm.pages)
		so->batch_offset = -1;

	ret = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
	if (ret)
		return ret;

	if (so->vma->node.start != so->batch_offset) {
		ret = render_state_setup(so, req->i915);
		if (ret)
			goto err_unpin;
	}

	ret = req->engine->emit_bb_start(req,
					 so->batch_offset, so->batch_size,
					 I915_DISPATCH_SECURE);
	if (ret)
		goto err_unpin;

	if (so->aux_size > 8) {
		ret = req->engine->emit_bb_start(req,
						 so->aux_offset, so->aux_size,
						 I915_DISPATCH_SECURE);
		if (ret)
			goto err_unpin;
	}

	i915_vma_move_to_active(so->vma, req, 0);
err_unpin:
	i915_vma_unpin(so->vma);
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson14165.89%857.14%


Mika Kuoppala3415.89%214.29%


Arun Siluvery2913.55%17.14%


Oscar Mateo41.87%17.14%


John Harrison41.87%17.14%


Tvrtko A. Ursulin20.93%17.14%


Total214100.00%14100.00%






void i915_gem_render_state_fini(struct intel_engine_cs *engine)
{
	struct intel_render_state *so;
	struct drm_i915_gem_object *obj;

	so = fetch_and_zero(&engine->render_state);
	if (!so)
		return;

	obj = so->vma->obj;

	i915_vma_close(so->vma);
	__i915_gem_object_release_unless_active(obj);

	kfree(so);
}

Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson5895.08%375.00%


Mika Kuoppala34.92%125.00%


Total61100.00%4100.00%




Overall Contributors
PersonTokensPropCommitsCommitProp
Chris Wilson59357.85%1450.00%


Mika Kuoppala22321.76%310.71%


Arun Siluvery17216.78%27.14%


Oscar Mateo141.37%13.57%


Armin Reese70.68%13.57%


John Harrison40.39%13.57%


Joonas Lahtinen40.39%13.57%


Tvrtko A. Ursulin40.39%310.71%


Dave Gordon30.29%13.57%


Masahiro Yamada10.10%13.57%


Total1025100.00%28100.00%


Directory: drivers/gpu/drm/i915



Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.