radeon_sa.c 11.1 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
/*
 * Copyright 2011 Red Hat Inc.
 * All Rights Reserved.
 *
 * 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
 * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 */
/*
 * Authors:
 *    Jerome Glisse <glisse@freedesktop.org>
 */
30 31 32 33 34 35 36 37 38 39 40 41 42 43
/* Algorithm:
 *
 * We store the last allocated bo in "hole", we always try to allocate
 * after the last allocated bo. Principle is that in a linear GPU ring
 * progression was is after last is the oldest bo we allocated and thus
 * the first one that should no longer be in use by the GPU.
 *
 * If it's not the case we skip over the bo after last to the closest
 * done bo if such one exist. If none exist and we are not asked to
 * block we report failure to allocate.
 *
 * If we are asked to block we wait on all the oldest fence of all
 * rings. We just wait for any of those fence to complete.
 */
44
#include <drm/drmP.h>
45 46
#include "radeon.h"

47 48 49
static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo);
static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager);

50 51
int radeon_sa_bo_manager_init(struct radeon_device *rdev,
			      struct radeon_sa_manager *sa_manager,
52
			      unsigned size, u32 align, u32 domain)
53
{
54
	int i, r;
55

56
	init_waitqueue_head(&sa_manager->wq);
57 58 59
	sa_manager->bo = NULL;
	sa_manager->size = size;
	sa_manager->domain = domain;
60
	sa_manager->align = align;
61 62 63 64 65
	sa_manager->hole = &sa_manager->olist;
	INIT_LIST_HEAD(&sa_manager->olist);
	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
		INIT_LIST_HEAD(&sa_manager->flist[i]);
	}
66

67
	r = radeon_bo_create(rdev, size, align, true,
68
			     domain, NULL, &sa_manager->bo);
69 70 71 72 73 74 75 76 77 78 79 80 81
	if (r) {
		dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r);
		return r;
	}

	return r;
}

void radeon_sa_bo_manager_fini(struct radeon_device *rdev,
			       struct radeon_sa_manager *sa_manager)
{
	struct radeon_sa_bo *sa_bo, *tmp;

82 83 84 85 86 87
	if (!list_empty(&sa_manager->olist)) {
		sa_manager->hole = &sa_manager->olist,
		radeon_sa_bo_try_free(sa_manager);
		if (!list_empty(&sa_manager->olist)) {
			dev_err(rdev->dev, "sa_manager is not empty, clearing anyway\n");
		}
88
	}
89 90
	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->olist, olist) {
		radeon_sa_bo_remove_locked(sa_bo);
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141
	}
	radeon_bo_unref(&sa_manager->bo);
	sa_manager->size = 0;
}

int radeon_sa_bo_manager_start(struct radeon_device *rdev,
			       struct radeon_sa_manager *sa_manager)
{
	int r;

	if (sa_manager->bo == NULL) {
		dev_err(rdev->dev, "no bo for sa manager\n");
		return -EINVAL;
	}

	/* map the buffer */
	r = radeon_bo_reserve(sa_manager->bo, false);
	if (r) {
		dev_err(rdev->dev, "(%d) failed to reserve manager bo\n", r);
		return r;
	}
	r = radeon_bo_pin(sa_manager->bo, sa_manager->domain, &sa_manager->gpu_addr);
	if (r) {
		radeon_bo_unreserve(sa_manager->bo);
		dev_err(rdev->dev, "(%d) failed to pin manager bo\n", r);
		return r;
	}
	r = radeon_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
	radeon_bo_unreserve(sa_manager->bo);
	return r;
}

int radeon_sa_bo_manager_suspend(struct radeon_device *rdev,
				 struct radeon_sa_manager *sa_manager)
{
	int r;

	if (sa_manager->bo == NULL) {
		dev_err(rdev->dev, "no bo for sa manager\n");
		return -EINVAL;
	}

	r = radeon_bo_reserve(sa_manager->bo, false);
	if (!r) {
		radeon_bo_kunmap(sa_manager->bo);
		radeon_bo_unpin(sa_manager->bo);
		radeon_bo_unreserve(sa_manager->bo);
	}
	return r;
}

142 143
static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo)
{
144 145 146 147 148 149
	struct radeon_sa_manager *sa_manager = sa_bo->manager;
	if (sa_manager->hole == &sa_bo->olist) {
		sa_manager->hole = sa_bo->olist.prev;
	}
	list_del_init(&sa_bo->olist);
	list_del_init(&sa_bo->flist);
150 151 152 153
	radeon_fence_unref(&sa_bo->fence);
	kfree(sa_bo);
}

154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213
static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager)
{
	struct radeon_sa_bo *sa_bo, *tmp;

	if (sa_manager->hole->next == &sa_manager->olist)
		return;

	sa_bo = list_entry(sa_manager->hole->next, struct radeon_sa_bo, olist);
	list_for_each_entry_safe_from(sa_bo, tmp, &sa_manager->olist, olist) {
		if (sa_bo->fence == NULL || !radeon_fence_signaled(sa_bo->fence)) {
			return;
		}
		radeon_sa_bo_remove_locked(sa_bo);
	}
}

static inline unsigned radeon_sa_bo_hole_soffset(struct radeon_sa_manager *sa_manager)
{
	struct list_head *hole = sa_manager->hole;

	if (hole != &sa_manager->olist) {
		return list_entry(hole, struct radeon_sa_bo, olist)->eoffset;
	}
	return 0;
}

static inline unsigned radeon_sa_bo_hole_eoffset(struct radeon_sa_manager *sa_manager)
{
	struct list_head *hole = sa_manager->hole;

	if (hole->next != &sa_manager->olist) {
		return list_entry(hole->next, struct radeon_sa_bo, olist)->soffset;
	}
	return sa_manager->size;
}

static bool radeon_sa_bo_try_alloc(struct radeon_sa_manager *sa_manager,
				   struct radeon_sa_bo *sa_bo,
				   unsigned size, unsigned align)
{
	unsigned soffset, eoffset, wasted;

	soffset = radeon_sa_bo_hole_soffset(sa_manager);
	eoffset = radeon_sa_bo_hole_eoffset(sa_manager);
	wasted = (align - (soffset % align)) % align;

	if ((eoffset - soffset) >= (size + wasted)) {
		soffset += wasted;

		sa_bo->manager = sa_manager;
		sa_bo->soffset = soffset;
		sa_bo->eoffset = soffset + size;
		list_add(&sa_bo->olist, sa_manager->hole);
		INIT_LIST_HEAD(&sa_bo->flist);
		sa_manager->hole = &sa_bo->olist;
		return true;
	}
	return false;
}

214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
/**
 * radeon_sa_event - Check if we can stop waiting
 *
 * @sa_manager: pointer to the sa_manager
 * @size: number of bytes we want to allocate
 * @align: alignment we need to match
 *
 * Check if either there is a fence we can wait for or
 * enough free memory to satisfy the allocation directly
 */
static bool radeon_sa_event(struct radeon_sa_manager *sa_manager,
			    unsigned size, unsigned align)
{
	unsigned soffset, eoffset, wasted;
	int i;

	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
		if (!list_empty(&sa_manager->flist[i])) {
			return true;
		}
	}

	soffset = radeon_sa_bo_hole_soffset(sa_manager);
	eoffset = radeon_sa_bo_hole_eoffset(sa_manager);
	wasted = (align - (soffset % align)) % align;

	if ((eoffset - soffset) >= (size + wasted)) {
		return true;
	}

	return false;
}

247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
static bool radeon_sa_bo_next_hole(struct radeon_sa_manager *sa_manager,
				   struct radeon_fence **fences,
				   unsigned *tries)
{
	struct radeon_sa_bo *best_bo = NULL;
	unsigned i, soffset, best, tmp;

	/* if hole points to the end of the buffer */
	if (sa_manager->hole->next == &sa_manager->olist) {
		/* try again with its beginning */
		sa_manager->hole = &sa_manager->olist;
		return true;
	}

	soffset = radeon_sa_bo_hole_soffset(sa_manager);
	/* to handle wrap around we add sa_manager->size */
	best = sa_manager->size * 2;
	/* go over all fence list and try to find the closest sa_bo
	 * of the current last
	 */
	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
		struct radeon_sa_bo *sa_bo;

		if (list_empty(&sa_manager->flist[i])) {
			continue;
		}

		sa_bo = list_first_entry(&sa_manager->flist[i],
					 struct radeon_sa_bo, flist);

		if (!radeon_fence_signaled(sa_bo->fence)) {
			fences[i] = sa_bo->fence;
			continue;
		}

		/* limit the number of tries each ring gets */
		if (tries[i] > 2) {
			continue;
		}

		tmp = sa_bo->soffset;
		if (tmp < soffset) {
			/* wrap around, pretend it's after */
			tmp += sa_manager->size;
		}
		tmp -= soffset;
		if (tmp < best) {
			/* this sa bo is the closest one */
			best = tmp;
			best_bo = sa_bo;
		}
	}

	if (best_bo) {
		++tries[best_bo->fence->ring];
		sa_manager->hole = best_bo->olist.prev;

		/* we knew that this one is signaled,
		   so it's save to remote it */
		radeon_sa_bo_remove_locked(best_bo);
		return true;
	}
	return false;
}

312 313
int radeon_sa_bo_new(struct radeon_device *rdev,
		     struct radeon_sa_manager *sa_manager,
314
		     struct radeon_sa_bo **sa_bo,
315
		     unsigned size, unsigned align)
316
{
317 318
	struct radeon_fence *fences[RADEON_NUM_RINGS];
	unsigned tries[RADEON_NUM_RINGS];
319
	int i, r;
320

321
	BUG_ON(align > sa_manager->align);
322
	BUG_ON(size > sa_manager->size);
323 324

	*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
325 326 327 328 329 330 331
	if ((*sa_bo) == NULL) {
		return -ENOMEM;
	}
	(*sa_bo)->manager = sa_manager;
	(*sa_bo)->fence = NULL;
	INIT_LIST_HEAD(&(*sa_bo)->olist);
	INIT_LIST_HEAD(&(*sa_bo)->flist);
332

333
	spin_lock(&sa_manager->wq.lock);
334
	do {
335 336 337 338
		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
			fences[i] = NULL;
			tries[i] = 0;
		}
339

340 341
		do {
			radeon_sa_bo_try_free(sa_manager);
342

343 344
			if (radeon_sa_bo_try_alloc(sa_manager, *sa_bo,
						   size, align)) {
345
				spin_unlock(&sa_manager->wq.lock);
346
				return 0;
347 348
			}

349 350 351
			/* see if we can skip over some allocations */
		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));

352 353 354 355
		spin_unlock(&sa_manager->wq.lock);
		r = radeon_fence_wait_any(rdev, fences, false);
		spin_lock(&sa_manager->wq.lock);
		/* if we have nothing to wait for block */
356
		if (r == -ENOENT) {
357 358 359 360 361
			r = wait_event_interruptible_locked(
				sa_manager->wq, 
				radeon_sa_event(sa_manager, size, align)
			);
		}
362

363 364
	} while (!r);

365
	spin_unlock(&sa_manager->wq.lock);
366 367 368
	kfree(*sa_bo);
	*sa_bo = NULL;
	return r;
369 370
}

371 372
void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo,
		       struct radeon_fence *fence)
373
{
374 375
	struct radeon_sa_manager *sa_manager;

376
	if (sa_bo == NULL || *sa_bo == NULL) {
377
		return;
378
	}
379

380
	sa_manager = (*sa_bo)->manager;
381
	spin_lock(&sa_manager->wq.lock);
382
	if (fence && !radeon_fence_signaled(fence)) {
383
		(*sa_bo)->fence = radeon_fence_ref(fence);
384 385
		list_add_tail(&(*sa_bo)->flist,
			      &sa_manager->flist[fence->ring]);
386 387 388
	} else {
		radeon_sa_bo_remove_locked(*sa_bo);
	}
389 390
	wake_up_all_locked(&sa_manager->wq);
	spin_unlock(&sa_manager->wq.lock);
391
	*sa_bo = NULL;
392
}
393 394 395 396 397 398 399

#if defined(CONFIG_DEBUG_FS)
void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager,
				  struct seq_file *m)
{
	struct radeon_sa_bo *i;

400
	spin_lock(&sa_manager->wq.lock);
401
	list_for_each_entry(i, &sa_manager->olist, olist) {
402 403
		uint64_t soffset = i->soffset + sa_manager->gpu_addr;
		uint64_t eoffset = i->eoffset + sa_manager->gpu_addr;
404 405
		if (&i->olist == sa_manager->hole) {
			seq_printf(m, ">");
406
		} else {
407 408
			seq_printf(m, " ");
		}
409 410
		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
			   soffset, eoffset, eoffset - soffset);
411 412 413
		if (i->fence) {
			seq_printf(m, " protected by 0x%016llx on ring %d",
				   i->fence->seq, i->fence->ring);
414
		}
415
		seq_printf(m, "\n");
416
	}
417
	spin_unlock(&sa_manager->wq.lock);
418 419
}
#endif
新手
引导
客服 返回
顶部