radeon_fence.c 10.1 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 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
/*
 * Copyright 2009 Jerome Glisse.
 * 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>
 *    Dave Airlie
 */
#include <linux/seq_file.h>
#include <asm/atomic.h>
#include <linux/wait.h>
#include <linux/list.h>
#include <linux/kref.h>
#include "drmP.h"
#include "drm.h"
#include "radeon_reg.h"
#include "radeon.h"

int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
{
	unsigned long irq_flags;

	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	if (fence->emited) {
		write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
		return 0;
	}
	fence->seq = atomic_add_return(1, &rdev->fence_drv.seq);
	if (!rdev->cp.ready) {
		/* FIXME: cp is not running assume everythings is done right
		 * away
		 */
		WREG32(rdev->fence_drv.scratch_reg, fence->seq);
	} else {
		radeon_fence_ring_emit(rdev, fence);
	}
	fence->emited = true;
	fence->timeout = jiffies + ((2000 * HZ) / 1000);
	list_del(&fence->list);
	list_add_tail(&fence->list, &rdev->fence_drv.emited);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	return 0;
}

static bool radeon_fence_poll_locked(struct radeon_device *rdev)
{
	struct radeon_fence *fence;
	struct list_head *i, *n;
	uint32_t seq;
	bool wake = false;

	if (rdev == NULL) {
		return true;
	}
	if (rdev->shutdown) {
		return true;
	}
	seq = RREG32(rdev->fence_drv.scratch_reg);
	rdev->fence_drv.last_seq = seq;
	n = NULL;
	list_for_each(i, &rdev->fence_drv.emited) {
		fence = list_entry(i, struct radeon_fence, list);
		if (fence->seq == seq) {
			n = i;
			break;
		}
	}
	/* all fence previous to this one are considered as signaled */
	if (n) {
		i = n;
		do {
			n = i->prev;
			list_del(i);
			list_add_tail(i, &rdev->fence_drv.signaled);
			fence = list_entry(i, struct radeon_fence, list);
			fence->signaled = true;
			i = n;
		} while (i != &rdev->fence_drv.emited);
		wake = true;
	}
	return wake;
}

static void radeon_fence_destroy(struct kref *kref)
{
	unsigned long irq_flags;
        struct radeon_fence *fence;

	fence = container_of(kref, struct radeon_fence, kref);
	write_lock_irqsave(&fence->rdev->fence_drv.lock, irq_flags);
	list_del(&fence->list);
	fence->emited = false;
	write_unlock_irqrestore(&fence->rdev->fence_drv.lock, irq_flags);
	kfree(fence);
}

int radeon_fence_create(struct radeon_device *rdev, struct radeon_fence **fence)
{
	unsigned long irq_flags;

	*fence = kmalloc(sizeof(struct radeon_fence), GFP_KERNEL);
	if ((*fence) == NULL) {
		return -ENOMEM;
	}
	kref_init(&((*fence)->kref));
	(*fence)->rdev = rdev;
	(*fence)->emited = false;
	(*fence)->signaled = false;
	(*fence)->seq = 0;
	INIT_LIST_HEAD(&(*fence)->list);

	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	list_add_tail(&(*fence)->list, &rdev->fence_drv.created);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	return 0;
}


bool radeon_fence_signaled(struct radeon_fence *fence)
{
	struct radeon_device *rdev = fence->rdev;
	unsigned long irq_flags;
	bool signaled = false;

	if (rdev->gpu_lockup) {
		return true;
	}
	if (fence == NULL) {
		return true;
	}
	write_lock_irqsave(&fence->rdev->fence_drv.lock, irq_flags);
	signaled = fence->signaled;
	/* if we are shuting down report all fence as signaled */
	if (fence->rdev->shutdown) {
		signaled = true;
	}
	if (!fence->emited) {
		WARN(1, "Querying an unemited fence : %p !\n", fence);
		signaled = true;
	}
	if (!signaled) {
		radeon_fence_poll_locked(fence->rdev);
		signaled = fence->signaled;
	}
	write_unlock_irqrestore(&fence->rdev->fence_drv.lock, irq_flags);
	return signaled;
}

int radeon_fence_wait(struct radeon_fence *fence, bool interruptible)
{
	struct radeon_device *rdev;
	unsigned long cur_jiffies;
	unsigned long timeout;
	bool expired = false;
	int r;


	if (fence == NULL) {
		WARN(1, "Querying an invalid fence : %p !\n", fence);
		return 0;
	}
	rdev = fence->rdev;
	if (radeon_fence_signaled(fence)) {
		return 0;
	}
retry:
	cur_jiffies = jiffies;
	timeout = HZ / 100;
	if (time_after(fence->timeout, cur_jiffies)) {
		timeout = fence->timeout - cur_jiffies;
	}
	if (interruptible) {
		r = wait_event_interruptible_timeout(rdev->fence_drv.queue,
				radeon_fence_signaled(fence), timeout);
		if (unlikely(r == -ERESTARTSYS)) {
198
			return -EBUSY;
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
		}
	} else {
		r = wait_event_timeout(rdev->fence_drv.queue,
			 radeon_fence_signaled(fence), timeout);
	}
	if (unlikely(!radeon_fence_signaled(fence))) {
		if (unlikely(r == 0)) {
			expired = true;
		}
		if (unlikely(expired)) {
			timeout = 1;
			if (time_after(cur_jiffies, fence->timeout)) {
				timeout = cur_jiffies - fence->timeout;
			}
			timeout = jiffies_to_msecs(timeout);
			if (timeout > 500) {
				DRM_ERROR("fence(%p:0x%08X) %lums timeout "
					  "going to reset GPU\n",
					  fence, fence->seq, timeout);
				radeon_gpu_reset(rdev);
				WREG32(rdev->fence_drv.scratch_reg, fence->seq);
			}
		}
		goto retry;
	}
	if (unlikely(expired)) {
		rdev->fence_drv.count_timeout++;
		cur_jiffies = jiffies;
		timeout = 1;
		if (time_after(cur_jiffies, fence->timeout)) {
			timeout = cur_jiffies - fence->timeout;
		}
		timeout = jiffies_to_msecs(timeout);
		DRM_ERROR("fence(%p:0x%08X) %lums timeout\n",
			  fence, fence->seq, timeout);
		DRM_ERROR("last signaled fence(0x%08X)\n",
			  rdev->fence_drv.last_seq);
	}
	return 0;
}

int radeon_fence_wait_next(struct radeon_device *rdev)
{
	unsigned long irq_flags;
	struct radeon_fence *fence;
	int r;

	if (rdev->gpu_lockup) {
		return 0;
	}
	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	if (list_empty(&rdev->fence_drv.emited)) {
		write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
		return 0;
	}
	fence = list_entry(rdev->fence_drv.emited.next,
			   struct radeon_fence, list);
	radeon_fence_ref(fence);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	r = radeon_fence_wait(fence, false);
	radeon_fence_unref(&fence);
	return r;
}

int radeon_fence_wait_last(struct radeon_device *rdev)
{
	unsigned long irq_flags;
	struct radeon_fence *fence;
	int r;

	if (rdev->gpu_lockup) {
		return 0;
	}
	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	if (list_empty(&rdev->fence_drv.emited)) {
		write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
		return 0;
	}
	fence = list_entry(rdev->fence_drv.emited.prev,
			   struct radeon_fence, list);
	radeon_fence_ref(fence);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	r = radeon_fence_wait(fence, false);
	radeon_fence_unref(&fence);
	return r;
}

struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence)
{
	kref_get(&fence->kref);
	return fence;
}

void radeon_fence_unref(struct radeon_fence **fence)
{
	struct radeon_fence *tmp = *fence;

	*fence = NULL;
	if (tmp) {
		kref_put(&tmp->kref, &radeon_fence_destroy);
	}
}

void radeon_fence_process(struct radeon_device *rdev)
{
	unsigned long irq_flags;
	bool wake;

	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	wake = radeon_fence_poll_locked(rdev);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	if (wake) {
		wake_up_all(&rdev->fence_drv.queue);
	}
}

int radeon_fence_driver_init(struct radeon_device *rdev)
{
	unsigned long irq_flags;
	int r;

	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	r = radeon_scratch_get(rdev, &rdev->fence_drv.scratch_reg);
	if (r) {
		DRM_ERROR("Fence failed to get a scratch register.");
		write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
		return r;
	}
	WREG32(rdev->fence_drv.scratch_reg, 0);
	atomic_set(&rdev->fence_drv.seq, 0);
	INIT_LIST_HEAD(&rdev->fence_drv.created);
	INIT_LIST_HEAD(&rdev->fence_drv.emited);
	INIT_LIST_HEAD(&rdev->fence_drv.signaled);
	rdev->fence_drv.count_timeout = 0;
	init_waitqueue_head(&rdev->fence_drv.queue);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	if (radeon_debugfs_fence_init(rdev)) {
		DRM_ERROR("Failed to register debugfs file for fence !\n");
	}
	return 0;
}

void radeon_fence_driver_fini(struct radeon_device *rdev)
{
	unsigned long irq_flags;

	wake_up_all(&rdev->fence_drv.queue);
	write_lock_irqsave(&rdev->fence_drv.lock, irq_flags);
	radeon_scratch_free(rdev, rdev->fence_drv.scratch_reg);
	write_unlock_irqrestore(&rdev->fence_drv.lock, irq_flags);
	DRM_INFO("radeon: fence finalized\n");
}


/*
 * Fence debugfs
 */
#if defined(CONFIG_DEBUG_FS)
static int radeon_debugfs_fence_info(struct seq_file *m, void *data)
{
	struct drm_info_node *node = (struct drm_info_node *)m->private;
	struct drm_device *dev = node->minor->dev;
	struct radeon_device *rdev = dev->dev_private;
	struct radeon_fence *fence;

	seq_printf(m, "Last signaled fence 0x%08X\n",
		   RREG32(rdev->fence_drv.scratch_reg));
	if (!list_empty(&rdev->fence_drv.emited)) {
		   fence = list_entry(rdev->fence_drv.emited.prev,
				      struct radeon_fence, list);
		   seq_printf(m, "Last emited fence %p with 0x%08X\n",
			      fence,  fence->seq);
	}
	return 0;
}

static struct drm_info_list radeon_debugfs_fence_list[] = {
	{"radeon_fence_info", &radeon_debugfs_fence_info, 0, NULL},
};
#endif

int radeon_debugfs_fence_init(struct radeon_device *rdev)
{
#if defined(CONFIG_DEBUG_FS)
	return radeon_debugfs_add_files(rdev, radeon_debugfs_fence_list, 1);
#else
	return 0;
#endif
}