blk-mq-sysfs.c 11.4 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
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>

#include <linux/blk-mq.h>
#include "blk-mq.h"
#include "blk-mq-tag.h"

static void blk_mq_sysfs_release(struct kobject *kobj)
{
}

struct blk_mq_ctx_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct blk_mq_ctx *, char *);
	ssize_t (*store)(struct blk_mq_ctx *, const char *, size_t);
};

struct blk_mq_hw_ctx_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct blk_mq_hw_ctx *, char *);
	ssize_t (*store)(struct blk_mq_hw_ctx *, const char *, size_t);
};

static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
				 char *page)
{
	struct blk_mq_ctx_sysfs_entry *entry;
	struct blk_mq_ctx *ctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
	q = ctx->queue;

	if (!entry->show)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->show(ctx, page);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
				  const char *page, size_t length)
{
	struct blk_mq_ctx_sysfs_entry *entry;
	struct blk_mq_ctx *ctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
	q = ctx->queue;

	if (!entry->store)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->store(ctx, page, length);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
				    struct attribute *attr, char *page)
{
	struct blk_mq_hw_ctx_sysfs_entry *entry;
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
	q = hctx->queue;

	if (!entry->show)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->show(hctx, page);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
				     struct attribute *attr, const char *page,
				     size_t length)
{
	struct blk_mq_hw_ctx_sysfs_entry *entry;
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q;
	ssize_t res;

	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
	q = hctx->queue;

	if (!entry->store)
		return -EIO;

	res = -ENOENT;
	mutex_lock(&q->sysfs_lock);
	if (!blk_queue_dying(q))
		res = entry->store(hctx, page, length);
	mutex_unlock(&q->sysfs_lock);
	return res;
}

static ssize_t blk_mq_sysfs_dispatched_show(struct blk_mq_ctx *ctx, char *page)
{
	return sprintf(page, "%lu %lu\n", ctx->rq_dispatched[1],
				ctx->rq_dispatched[0]);
}

static ssize_t blk_mq_sysfs_merged_show(struct blk_mq_ctx *ctx, char *page)
{
	return sprintf(page, "%lu\n", ctx->rq_merged);
}

static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
{
	return sprintf(page, "%lu %lu\n", ctx->rq_completed[1],
				ctx->rq_completed[0]);
}

static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
{
	struct request *rq;
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163
	int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);

	list_for_each_entry(rq, list, queuelist) {
		const int rq_len = 2 * sizeof(rq) + 2;

		/* if the output will be truncated */
		if (PAGE_SIZE - 1 < len + rq_len) {
			/* backspacing if it can't hold '\t...\n' */
			if (PAGE_SIZE - 1 < len + 5)
				len -= rq_len;
			len += snprintf(page + len, PAGE_SIZE - 1 - len,
					"\t...\n");
			break;
		}
		len += snprintf(page + len, PAGE_SIZE - 1 - len,
				"\t%p\n", rq);
	}

	return len;
164 165 166 167 168 169 170 171 172 173 174 175 176
}

static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
{
	ssize_t ret;

	spin_lock(&ctx->lock);
	ret = sysfs_list_show(page, &ctx->rq_list, "CTX pending");
	spin_unlock(&ctx->lock);

	return ret;
}

177 178 179 180 181
static ssize_t blk_mq_hw_sysfs_poll_show(struct blk_mq_hw_ctx *hctx, char *page)
{
	return sprintf(page, "invoked=%lu, success=%lu\n", hctx->poll_invoked, hctx->poll_success);
}

182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
static ssize_t blk_mq_hw_sysfs_queued_show(struct blk_mq_hw_ctx *hctx,
					   char *page)
{
	return sprintf(page, "%lu\n", hctx->queued);
}

static ssize_t blk_mq_hw_sysfs_run_show(struct blk_mq_hw_ctx *hctx, char *page)
{
	return sprintf(page, "%lu\n", hctx->run);
}

static ssize_t blk_mq_hw_sysfs_dispatched_show(struct blk_mq_hw_ctx *hctx,
					       char *page)
{
	char *start_page = page;
	int i;

	page += sprintf(page, "%8u\t%lu\n", 0U, hctx->dispatched[0]);

	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER; i++) {
		unsigned long d = 1U << (i - 1);

		page += sprintf(page, "%8lu\t%lu\n", d, hctx->dispatched[i]);
	}

	return page - start_page;
}

static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
					    char *page)
{
	ssize_t ret;

	spin_lock(&hctx->lock);
	ret = sysfs_list_show(page, &hctx->dispatch, "HCTX pending");
	spin_unlock(&hctx->lock);

	return ret;
}

static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
{
	return blk_mq_tag_sysfs_show(hctx->tags, page);
}

227 228 229 230 231
static ssize_t blk_mq_hw_sysfs_active_show(struct blk_mq_hw_ctx *hctx, char *page)
{
	return sprintf(page, "%u\n", atomic_read(&hctx->nr_active));
}

232 233
static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
{
234
	unsigned int i, first = 1;
235 236
	ssize_t ret = 0;

237
	for_each_cpu(i, hctx->cpumask) {
238 239 240 241 242 243 244 245 246 247 248 249
		if (first)
			ret += sprintf(ret + page, "%u", i);
		else
			ret += sprintf(ret + page, ", %u", i);

		first = 0;
	}

	ret += sprintf(ret + page, "\n");
	return ret;
}

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
static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
	.attr = {.name = "dispatched", .mode = S_IRUGO },
	.show = blk_mq_sysfs_dispatched_show,
};
static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_merged = {
	.attr = {.name = "merged", .mode = S_IRUGO },
	.show = blk_mq_sysfs_merged_show,
};
static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_completed = {
	.attr = {.name = "completed", .mode = S_IRUGO },
	.show = blk_mq_sysfs_completed_show,
};
static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_rq_list = {
	.attr = {.name = "rq_list", .mode = S_IRUGO },
	.show = blk_mq_sysfs_rq_list_show,
};

static struct attribute *default_ctx_attrs[] = {
	&blk_mq_sysfs_dispatched.attr,
	&blk_mq_sysfs_merged.attr,
	&blk_mq_sysfs_completed.attr,
	&blk_mq_sysfs_rq_list.attr,
	NULL,
};

static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_queued = {
	.attr = {.name = "queued", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_queued_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_run = {
	.attr = {.name = "run", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_run_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_dispatched = {
	.attr = {.name = "dispatched", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_dispatched_show,
};
287 288 289 290
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_active = {
	.attr = {.name = "active", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_active_show,
};
291 292 293 294 295 296 297 298
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
	.attr = {.name = "pending", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_rq_list_show,
};
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
	.attr = {.name = "tags", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_tags_show,
};
299 300 301 302
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
	.attr = {.name = "cpu_list", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_cpus_show,
};
303 304 305 306
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
	.attr = {.name = "io_poll", .mode = S_IRUGO },
	.show = blk_mq_hw_sysfs_poll_show,
};
307 308 309 310 311 312 313

static struct attribute *default_hw_ctx_attrs[] = {
	&blk_mq_hw_sysfs_queued.attr,
	&blk_mq_hw_sysfs_run.attr,
	&blk_mq_hw_sysfs_dispatched.attr,
	&blk_mq_hw_sysfs_pending.attr,
	&blk_mq_hw_sysfs_tags.attr,
314
	&blk_mq_hw_sysfs_cpus.attr,
315
	&blk_mq_hw_sysfs_active.attr,
316
	&blk_mq_hw_sysfs_poll.attr,
317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
	NULL,
};

static const struct sysfs_ops blk_mq_sysfs_ops = {
	.show	= blk_mq_sysfs_show,
	.store	= blk_mq_sysfs_store,
};

static const struct sysfs_ops blk_mq_hw_sysfs_ops = {
	.show	= blk_mq_hw_sysfs_show,
	.store	= blk_mq_hw_sysfs_store,
};

static struct kobj_type blk_mq_ktype = {
	.sysfs_ops	= &blk_mq_sysfs_ops,
	.release	= blk_mq_sysfs_release,
};

static struct kobj_type blk_mq_ctx_ktype = {
	.sysfs_ops	= &blk_mq_sysfs_ops,
	.default_attrs	= default_ctx_attrs,
338
	.release	= blk_mq_sysfs_release,
339 340 341 342 343
};

static struct kobj_type blk_mq_hw_ktype = {
	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
	.default_attrs	= default_hw_ctx_attrs,
344
	.release	= blk_mq_sysfs_release,
345 346
};

347
static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
348 349 350 351
{
	struct blk_mq_ctx *ctx;
	int i;

352
	if (!hctx->nr_ctx)
353 354 355 356 357 358 359 360
		return;

	hctx_for_each_ctx(hctx, ctx, i)
		kobject_del(&ctx->kobj);

	kobject_del(&hctx->kobj);
}

361
static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
362 363 364 365 366
{
	struct request_queue *q = hctx->queue;
	struct blk_mq_ctx *ctx;
	int i, ret;

367
	if (!hctx->nr_ctx)
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382
		return 0;

	ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
	if (ret)
		return ret;

	hctx_for_each_ctx(hctx, ctx, i) {
		ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu);
		if (ret)
			break;
	}

	return ret;
}

383
static void __blk_mq_unregister_disk(struct gendisk *disk)
384 385
{
	struct request_queue *q = disk->queue;
386 387 388 389 390
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
	int i, j;

	queue_for_each_hw_ctx(q, hctx, i) {
391 392 393
		blk_mq_unregister_hctx(hctx);

		hctx_for_each_ctx(hctx, ctx, j)
394
			kobject_put(&ctx->kobj);
395

396 397
		kobject_put(&hctx->kobj);
	}
398 399 400

	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
	kobject_del(&q->mq_kobj);
401
	kobject_put(&q->mq_kobj);
402 403

	kobject_put(&disk_to_dev(disk)->kobj);
404 405

	q->mq_sysfs_init_done = false;
406 407 408 409 410 411
}

void blk_mq_unregister_disk(struct gendisk *disk)
{
	blk_mq_disable_hotplug();
	__blk_mq_unregister_disk(disk);
412
	blk_mq_enable_hotplug();
413 414
}

415 416 417 418 419
void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
{
	kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
}

420 421 422
static void blk_mq_sysfs_init(struct request_queue *q)
{
	struct blk_mq_ctx *ctx;
423
	int cpu;
424 425 426

	kobject_init(&q->mq_kobj, &blk_mq_ktype);

427 428
	for_each_possible_cpu(cpu) {
		ctx = per_cpu_ptr(q->queue_ctx, cpu);
429
		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
430
	}
431 432
}

433 434 435 436 437
int blk_mq_register_disk(struct gendisk *disk)
{
	struct device *dev = disk_to_dev(disk);
	struct request_queue *q = disk->queue;
	struct blk_mq_hw_ctx *hctx;
438
	int ret, i;
439

440 441
	blk_mq_disable_hotplug();

442
	blk_mq_sysfs_init(q);
443 444 445

	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
	if (ret < 0)
446
		goto out;
447 448 449 450

	kobject_uevent(&q->mq_kobj, KOBJ_ADD);

	queue_for_each_hw_ctx(q, hctx, i) {
451
		ret = blk_mq_register_hctx(hctx);
452 453 454 455
		if (ret)
			break;
	}

456
	if (ret)
457
		__blk_mq_unregister_disk(disk);
458 459 460 461
	else
		q->mq_sysfs_init_done = true;
out:
	blk_mq_enable_hotplug();
462

463
	return ret;
464
}
465
EXPORT_SYMBOL_GPL(blk_mq_register_disk);
466 467 468 469 470 471

void blk_mq_sysfs_unregister(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

472 473 474
	if (!q->mq_sysfs_init_done)
		return;

475 476 477 478 479 480 481 482 483
	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_unregister_hctx(hctx);
}

int blk_mq_sysfs_register(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i, ret = 0;

484 485 486
	if (!q->mq_sysfs_init_done)
		return ret;

487 488 489 490 491 492 493 494
	queue_for_each_hw_ctx(q, hctx, i) {
		ret = blk_mq_register_hctx(hctx);
		if (ret)
			break;
	}

	return ret;
}