intel_engine_cs.c 9.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
/*
 * Copyright © 2016 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.
 *
 */

#include "i915_drv.h"
#include "intel_ringbuffer.h"
#include "intel_lrc.h"

static const struct engine_info {
	const char *name;
	unsigned exec_id;
	unsigned guc_id;
	u32 mmio_base;
	unsigned irq_shift;
	int (*init_legacy)(struct intel_engine_cs *engine);
	int (*init_execlists)(struct intel_engine_cs *engine);
} intel_engines[] = {
	[RCS] = {
		.name = "render ring",
		.exec_id = I915_EXEC_RENDER,
		.guc_id = GUC_RENDER_ENGINE,
		.mmio_base = RENDER_RING_BASE,
		.irq_shift = GEN8_RCS_IRQ_SHIFT,
		.init_execlists = logical_render_ring_init,
		.init_legacy = intel_init_render_ring_buffer,
	},
	[BCS] = {
		.name = "blitter ring",
		.exec_id = I915_EXEC_BLT,
		.guc_id = GUC_BLITTER_ENGINE,
		.mmio_base = BLT_RING_BASE,
		.irq_shift = GEN8_BCS_IRQ_SHIFT,
		.init_execlists = logical_xcs_ring_init,
		.init_legacy = intel_init_blt_ring_buffer,
	},
	[VCS] = {
		.name = "bsd ring",
		.exec_id = I915_EXEC_BSD,
		.guc_id = GUC_VIDEO_ENGINE,
		.mmio_base = GEN6_BSD_RING_BASE,
		.irq_shift = GEN8_VCS1_IRQ_SHIFT,
		.init_execlists = logical_xcs_ring_init,
		.init_legacy = intel_init_bsd_ring_buffer,
	},
	[VCS2] = {
		.name = "bsd2 ring",
		.exec_id = I915_EXEC_BSD,
		.guc_id = GUC_VIDEO_ENGINE2,
		.mmio_base = GEN8_BSD2_RING_BASE,
		.irq_shift = GEN8_VCS2_IRQ_SHIFT,
		.init_execlists = logical_xcs_ring_init,
		.init_legacy = intel_init_bsd2_ring_buffer,
	},
	[VECS] = {
		.name = "video enhancement ring",
		.exec_id = I915_EXEC_VEBOX,
		.guc_id = GUC_VIDEOENHANCE_ENGINE,
		.mmio_base = VEBOX_RING_BASE,
		.irq_shift = GEN8_VECS_IRQ_SHIFT,
		.init_execlists = logical_xcs_ring_init,
		.init_legacy = intel_init_vebox_ring_buffer,
	},
};

static struct intel_engine_cs *
intel_engine_setup(struct drm_i915_private *dev_priv,
		   enum intel_engine_id id)
{
	const struct engine_info *info = &intel_engines[id];
	struct intel_engine_cs *engine = &dev_priv->engine[id];

	engine->id = id;
	engine->i915 = dev_priv;
	engine->name = info->name;
	engine->exec_id = info->exec_id;
	engine->hw_id = engine->guc_id = info->guc_id;
	engine->mmio_base = info->mmio_base;
	engine->irq_shift = info->irq_shift;

	return engine;
}

/**
 * intel_engines_init() - allocate, populate and init the Engine Command Streamers
 * @dev: DRM device.
 *
 * Return: non-zero if the initialization failed.
 */
int intel_engines_init(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
112
	struct intel_device_info *device_info = mkwrite_device_info(dev_priv);
113 114 115 116 117
	unsigned int mask = 0;
	int (*init)(struct intel_engine_cs *engine);
	unsigned int i;
	int ret;

118
	WARN_ON(INTEL_INFO(dev_priv)->ring_mask == 0);
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
	WARN_ON(INTEL_INFO(dev_priv)->ring_mask &
		GENMASK(sizeof(mask) * BITS_PER_BYTE - 1, I915_NUM_ENGINES));

	for (i = 0; i < ARRAY_SIZE(intel_engines); i++) {
		if (!HAS_ENGINE(dev_priv, i))
			continue;

		if (i915.enable_execlists)
			init = intel_engines[i].init_execlists;
		else
			init = intel_engines[i].init_legacy;

		if (!init)
			continue;

		ret = init(intel_engine_setup(dev_priv, i));
		if (ret)
			goto cleanup;

		mask |= ENGINE_MASK(i);
	}

	/*
	 * Catch failures to update intel_engines table when the new engines
	 * are added to the driver by a warning and disabling the forgotten
	 * engines.
	 */
146 147 148 149
	if (WARN_ON(mask != INTEL_INFO(dev_priv)->ring_mask))
		device_info->ring_mask = mask;

	device_info->num_rings = hweight32(mask);
150 151 152 153 154 155 156 157

	return 0;

cleanup:
	for (i = 0; i < I915_NUM_ENGINES; i++) {
		if (i915.enable_execlists)
			intel_logical_ring_cleanup(&dev_priv->engine[i]);
		else
158
			intel_engine_cleanup(&dev_priv->engine[i]);
159 160 161 162 163
	}

	return ret;
}

164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno)
{
	struct drm_i915_private *dev_priv = engine->i915;

	/* Our semaphore implementation is strictly monotonic (i.e. we proceed
	 * so long as the semaphore value in the register/page is greater
	 * than the sync value), so whenever we reset the seqno,
	 * so long as we reset the tracking semaphore value to 0, it will
	 * always be before the next request's seqno. If we don't reset
	 * the semaphore value, then when the seqno moves backwards all
	 * future waits will complete instantly (causing rendering corruption).
	 */
	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
		I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
		I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
		if (HAS_VEBOX(dev_priv))
			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
	}
182 183 184 185 186 187
	if (dev_priv->semaphore) {
		struct page *page = i915_vma_first_page(dev_priv->semaphore);
		void *semaphores;

		/* Semaphores are in noncoherent memory, flush to be safe */
		semaphores = kmap(page);
188 189
		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
190 191
		drm_clflush_virt_range(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
				       I915_NUM_ENGINES * gen8_semaphore_seqno_size);
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
		kunmap(page);
	}
	memset(engine->semaphore.sync_seqno, 0,
	       sizeof(engine->semaphore.sync_seqno));

	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
	if (engine->irq_seqno_barrier)
		engine->irq_seqno_barrier(engine);
	engine->last_submitted_seqno = seqno;

	engine->hangcheck.seqno = seqno;

	/* After manually advancing the seqno, fake the interrupt in case
	 * there are any waiters for that seqno.
	 */
	intel_engine_wakeup(engine);
}

210 211 212
void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
{
	memset(&engine->hangcheck, 0, sizeof(engine->hangcheck));
213
	clear_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings);
214 215
}

216 217 218 219 220 221
static void intel_engine_init_requests(struct intel_engine_cs *engine)
{
	init_request_active(&engine->last_request, NULL);
	INIT_LIST_HEAD(&engine->request_list);
}

222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
/**
 * intel_engines_setup_common - setup engine state not requiring hw access
 * @engine: Engine to setup.
 *
 * Initializes @engine@ structure members shared between legacy and execlists
 * submission modes which do not require hardware access.
 *
 * Typically done early in the submission mode specific engine setup stage.
 */
void intel_engine_setup_common(struct intel_engine_cs *engine)
{
	INIT_LIST_HEAD(&engine->buffers);
	INIT_LIST_HEAD(&engine->execlist_queue);
	spin_lock_init(&engine->execlist_lock);

237 238
	engine->fence_context = fence_context_alloc(1);

239
	intel_engine_init_requests(engine);
240
	intel_engine_init_hangcheck(engine);
241
	i915_gem_batch_pool_init(engine, &engine->batch_pool);
242 243
}

244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281
int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
{
	struct drm_i915_gem_object *obj;
	struct i915_vma *vma;
	int ret;

	WARN_ON(engine->scratch);

	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
	if (!obj)
		obj = i915_gem_object_create(&engine->i915->drm, size);
	if (IS_ERR(obj)) {
		DRM_ERROR("Failed to allocate scratch page\n");
		return PTR_ERR(obj);
	}

	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
	if (IS_ERR(vma)) {
		ret = PTR_ERR(vma);
		goto err_unref;
	}

	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
	if (ret)
		goto err_unref;

	engine->scratch = vma;
	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
			 engine->name, vma->node.start);
	return 0;

err_unref:
	i915_gem_object_put(obj);
	return ret;
}

static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
{
282
	i915_vma_unpin_and_release(&engine->scratch);
283 284
}

285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303
/**
 * intel_engines_init_common - initialize cengine state which might require hw access
 * @engine: Engine to initialize.
 *
 * Initializes @engine@ structure members shared between legacy and execlists
 * submission modes which do require hardware access.
 *
 * Typcally done at later stages of submission mode specific engine setup.
 *
 * Returns zero on success or an error code on failure.
 */
int intel_engine_init_common(struct intel_engine_cs *engine)
{
	int ret;

	ret = intel_engine_init_breadcrumbs(engine);
	if (ret)
		return ret;

304
	return intel_engine_init_cmd_parser(engine);
305
}
306 307 308 309 310 311 312 313 314 315

/**
 * intel_engines_cleanup_common - cleans up the engine state created by
 *                                the common initiailizers.
 * @engine: Engine to cleanup.
 *
 * This cleans up everything created by the common helpers.
 */
void intel_engine_cleanup_common(struct intel_engine_cs *engine)
{
316 317
	intel_engine_cleanup_scratch(engine);

318 319 320 321
	intel_engine_cleanup_cmd_parser(engine);
	intel_engine_fini_breadcrumbs(engine);
	i915_gem_batch_pool_fini(&engine->batch_pool);
}