intel_engine_cs.c 12.8 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
/*
 * 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;
32
	enum intel_engine_hw_id hw_id;
33 34 35 36 37 38 39 40
	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,
41
		.hw_id = RCS_HW,
42 43 44 45 46 47 48 49
		.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,
50
		.hw_id = BCS_HW,
51 52 53 54 55 56 57 58
		.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,
59
		.hw_id = VCS_HW,
60 61 62 63 64 65 66 67
		.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,
68
		.hw_id = VCS2_HW,
69 70 71 72 73 74 75 76
		.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,
77
		.hw_id = VECS_HW,
78 79 80 81 82 83 84
		.mmio_base = VEBOX_RING_BASE,
		.irq_shift = GEN8_VECS_IRQ_SHIFT,
		.init_execlists = logical_xcs_ring_init,
		.init_legacy = intel_init_vebox_ring_buffer,
	},
};

85
static int
86 87 88 89
intel_engine_setup(struct drm_i915_private *dev_priv,
		   enum intel_engine_id id)
{
	const struct engine_info *info = &intel_engines[id];
90 91 92 93 94 95
	struct intel_engine_cs *engine;

	GEM_BUG_ON(dev_priv->engine[id]);
	engine = kzalloc(sizeof(*engine), GFP_KERNEL);
	if (!engine)
		return -ENOMEM;
96 97 98 99 100

	engine->id = id;
	engine->i915 = dev_priv;
	engine->name = info->name;
	engine->exec_id = info->exec_id;
101
	engine->hw_id = engine->guc_id = info->hw_id;
102 103 104
	engine->mmio_base = info->mmio_base;
	engine->irq_shift = info->irq_shift;

105 106
	dev_priv->engine[id] = engine;
	return 0;
107 108 109 110 111 112 113 114 115 116 117
}

/**
 * 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);
118
	struct intel_device_info *device_info = mkwrite_device_info(dev_priv);
119
	unsigned int ring_mask = INTEL_INFO(dev_priv)->ring_mask;
120 121
	unsigned int mask = 0;
	int (*init)(struct intel_engine_cs *engine);
122 123
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
124 125 126
	unsigned int i;
	int ret;

127 128
	WARN_ON(ring_mask == 0);
	WARN_ON(ring_mask &
129 130 131 132 133 134 135 136 137 138 139 140 141 142
		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;

143 144 145 146 147
		ret = intel_engine_setup(dev_priv, i);
		if (ret)
			goto cleanup;

		ret = init(dev_priv->engine[i]);
148 149 150 151 152 153 154 155 156 157 158
		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.
	 */
159
	if (WARN_ON(mask != ring_mask))
160 161 162
		device_info->ring_mask = mask;

	device_info->num_rings = hweight32(mask);
163 164 165 166

	return 0;

cleanup:
167
	for_each_engine(engine, dev_priv, id) {
168
		if (i915.enable_execlists)
169
			intel_logical_ring_cleanup(engine);
170
		else
171
			intel_engine_cleanup(engine);
172 173 174 175 176
	}

	return ret;
}

177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194
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);
	}
195 196 197 198 199 200
	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);
201 202
		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
203 204
		drm_clflush_virt_range(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
				       I915_NUM_ENGINES * gen8_semaphore_seqno_size);
205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
		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);
}

223 224 225 226 227
void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
{
	memset(&engine->hangcheck, 0, sizeof(engine->hangcheck));
}

228 229 230 231 232 233
static void intel_engine_init_requests(struct intel_engine_cs *engine)
{
	init_request_active(&engine->last_request, NULL);
	INIT_LIST_HEAD(&engine->request_list);
}

234 235 236 237 238 239 240 241 242 243 244 245 246 247
/**
 * 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->execlist_queue);
	spin_lock_init(&engine->execlist_lock);

248
	engine->fence_context = dma_fence_context_alloc(1);
249

250
	intel_engine_init_requests(engine);
251
	intel_engine_init_hangcheck(engine);
252
	i915_gem_batch_pool_init(engine, &engine->batch_pool);
253 254

	intel_engine_init_cmd_parser(engine);
255 256
}

257 258 259 260 261 262 263 264 265 266
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)
267
		obj = i915_gem_object_create_internal(engine->i915, size);
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283
	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;
284 285
	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
			 engine->name, i915_ggtt_offset(vma));
286 287 288 289 290 291 292 293 294
	return 0;

err_unref:
	i915_gem_object_put(obj);
	return ret;
}

static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
{
295
	i915_vma_unpin_and_release(&engine->scratch);
296 297
}

298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
/**
 * 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;

317
	return 0;
318
}
319 320 321 322 323 324 325 326 327 328

/**
 * 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)
{
329 330
	intel_engine_cleanup_scratch(engine);

331
	intel_engine_fini_breadcrumbs(engine);
332
	intel_engine_cleanup_cmd_parser(engine);
333 334
	i915_gem_batch_pool_fini(&engine->batch_pool);
}
335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364

u64 intel_engine_get_active_head(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	u64 acthd;

	if (INTEL_GEN(dev_priv) >= 8)
		acthd = I915_READ64_2x32(RING_ACTHD(engine->mmio_base),
					 RING_ACTHD_UDW(engine->mmio_base));
	else if (INTEL_GEN(dev_priv) >= 4)
		acthd = I915_READ(RING_ACTHD(engine->mmio_base));
	else
		acthd = I915_READ(ACTHD);

	return acthd;
}

u64 intel_engine_get_last_batch_head(struct intel_engine_cs *engine)
{
	struct drm_i915_private *dev_priv = engine->i915;
	u64 bbaddr;

	if (INTEL_GEN(dev_priv) >= 8)
		bbaddr = I915_READ64_2x32(RING_BBADDR(engine->mmio_base),
					  RING_BBADDR_UDW(engine->mmio_base));
	else
		bbaddr = I915_READ(RING_BBADDR(engine->mmio_base));

	return bbaddr;
}
365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468

const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
{
	switch (type) {
	case I915_CACHE_NONE: return " uncached";
	case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
	case I915_CACHE_L3_LLC: return " L3+LLC";
	case I915_CACHE_WT: return " WT";
	default: return "";
	}
}

static inline uint32_t
read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
		  int subslice, i915_reg_t reg)
{
	uint32_t mcr;
	uint32_t ret;
	enum forcewake_domains fw_domains;

	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
						    FW_REG_READ);
	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
						     GEN8_MCR_SELECTOR,
						     FW_REG_READ | FW_REG_WRITE);

	spin_lock_irq(&dev_priv->uncore.lock);
	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);

	mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
	/*
	 * The HW expects the slice and sublice selectors to be reset to 0
	 * after reading out the registers.
	 */
	WARN_ON_ONCE(mcr & (GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK));
	mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
	mcr |= GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice);
	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);

	ret = I915_READ_FW(reg);

	mcr &= ~(GEN8_MCR_SLICE_MASK | GEN8_MCR_SUBSLICE_MASK);
	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);

	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
	spin_unlock_irq(&dev_priv->uncore.lock);

	return ret;
}

/* NB: please notice the memset */
void intel_engine_get_instdone(struct intel_engine_cs *engine,
			       struct intel_instdone *instdone)
{
	struct drm_i915_private *dev_priv = engine->i915;
	u32 mmio_base = engine->mmio_base;
	int slice;
	int subslice;

	memset(instdone, 0, sizeof(*instdone));

	switch (INTEL_GEN(dev_priv)) {
	default:
		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));

		if (engine->id != RCS)
			break;

		instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
		for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
			instdone->sampler[slice][subslice] =
				read_subslice_reg(dev_priv, slice, subslice,
						  GEN7_SAMPLER_INSTDONE);
			instdone->row[slice][subslice] =
				read_subslice_reg(dev_priv, slice, subslice,
						  GEN7_ROW_INSTDONE);
		}
		break;
	case 7:
		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));

		if (engine->id != RCS)
			break;

		instdone->slice_common = I915_READ(GEN7_SC_INSTDONE);
		instdone->sampler[0][0] = I915_READ(GEN7_SAMPLER_INSTDONE);
		instdone->row[0][0] = I915_READ(GEN7_ROW_INSTDONE);

		break;
	case 6:
	case 5:
	case 4:
		instdone->instdone = I915_READ(RING_INSTDONE(mmio_base));

		if (engine->id == RCS)
			/* HACK: Using the wrong struct member */
			instdone->slice_common = I915_READ(GEN4_INSTDONE1);
		break;
	case 3:
	case 2:
		instdone->instdone = I915_READ(GEN2_INSTDONE);
		break;
	}
}