blk-flush.c 16.6 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584
/*
 * Functions to sequence PREFLUSH and FUA writes.
 *
 * Copyright (C) 2011		Max Planck Institute for Gravitational Physics
 * Copyright (C) 2011		Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 *
 * REQ_{PREFLUSH|FUA} requests are decomposed to sequences consisted of three
 * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
 * properties and hardware capability.
 *
 * If a request doesn't have data, only REQ_PREFLUSH makes sense, which
 * indicates a simple flush request.  If there is data, REQ_PREFLUSH indicates
 * that the device cache should be flushed before the data is executed, and
 * REQ_FUA means that the data must be on non-volatile media on request
 * completion.
 *
 * If the device doesn't have writeback cache, PREFLUSH and FUA don't make any
 * difference.  The requests are either completed immediately if there's no data
 * or executed as normal requests otherwise.
 *
 * If the device has writeback cache and supports FUA, REQ_PREFLUSH is
 * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
 *
 * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH
 * is translated to PREFLUSH and REQ_FUA to POSTFLUSH.
 *
 * The actual execution of flush is double buffered.  Whenever a request
 * needs to execute PRE or POSTFLUSH, it queues at
 * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
 * REQ_OP_FLUSH is issued and the pending_idx is toggled.  When the flush
 * completes, all the requests which were pending are proceeded to the next
 * step.  This allows arbitrary merging of different types of PREFLUSH/FUA
 * requests.
 *
 * Currently, the following conditions are used to determine when to issue
 * flush.
 *
 * C1. At any given time, only one flush shall be in progress.  This makes
 *     double buffering sufficient.
 *
 * C2. Flush is deferred if any request is executing DATA of its sequence.
 *     This avoids issuing separate POSTFLUSHes for requests which shared
 *     PREFLUSH.
 *
 * C3. The second condition is ignored if there is a request which has
 *     waited longer than FLUSH_PENDING_TIMEOUT.  This is to avoid
 *     starvation in the unlikely case where there are continuous stream of
 *     FUA (without PREFLUSH) requests.
 *
 * For devices which support FUA, it isn't clear whether C2 (and thus C3)
 * is beneficial.
 *
 * Note that a sequenced PREFLUSH/FUA request with DATA is completed twice.
 * Once while executing DATA and again after the whole sequence is
 * complete.  The first completion updates the contained bio but doesn't
 * finish it so that the bio submitter is notified only after the whole
 * sequence is complete.  This is implemented by testing RQF_FLUSH_SEQ in
 * req_bio_endio().
 *
 * The above peculiarity requires that each PREFLUSH/FUA request has only one
 * bio attached to it, which is guaranteed as they aren't allowed to be
 * merged in the usual way.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/gfp.h>
#include <linux/blk-mq.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"

/* PREFLUSH/FUA sequences */
enum {
	REQ_FSEQ_PREFLUSH	= (1 << 0), /* pre-flushing in progress */
	REQ_FSEQ_DATA		= (1 << 1), /* data write in progress */
	REQ_FSEQ_POSTFLUSH	= (1 << 2), /* post-flushing in progress */
	REQ_FSEQ_DONE		= (1 << 3),

	REQ_FSEQ_ACTIONS	= REQ_FSEQ_PREFLUSH | REQ_FSEQ_DATA |
				  REQ_FSEQ_POSTFLUSH,

	/*
	 * If flush has been pending longer than the following timeout,
	 * it's issued even if flush_data requests are still in flight.
	 */
	FLUSH_PENDING_TIMEOUT	= 5 * HZ,
};

static bool blk_kick_flush(struct request_queue *q,
			   struct blk_flush_queue *fq);

static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
{
	unsigned int policy = 0;

	if (blk_rq_sectors(rq))
		policy |= REQ_FSEQ_DATA;

	if (fflags & (1UL << QUEUE_FLAG_WC)) {
		if (rq->cmd_flags & REQ_PREFLUSH)
			policy |= REQ_FSEQ_PREFLUSH;
		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
		    (rq->cmd_flags & REQ_FUA))
			policy |= REQ_FSEQ_POSTFLUSH;
	}
	return policy;
}

static unsigned int blk_flush_cur_seq(struct request *rq)
{
	return 1 << ffz(rq->flush.seq);
}

static void blk_flush_restore_request(struct request *rq)
{
	/*
	 * After flush data completion, @rq->bio is %NULL but we need to
	 * complete the bio again.  @rq->biotail is guaranteed to equal the
	 * original @rq->bio.  Restore it.
	 */
	rq->bio = rq->biotail;

	/* make @rq a normal request */
	rq->rq_flags &= ~RQF_FLUSH_SEQ;
	rq->end_io = rq->flush.saved_end_io;
}

static bool blk_flush_queue_rq(struct request *rq, bool add_front)
{
	if (rq->q->mq_ops) {
		blk_mq_add_to_requeue_list(rq, add_front, true);
		return false;
	} else {
		if (add_front)
			list_add(&rq->queuelist, &rq->q->queue_head);
		else
			list_add_tail(&rq->queuelist, &rq->q->queue_head);
		return true;
	}
}

/**
 * blk_flush_complete_seq - complete flush sequence
 * @rq: PREFLUSH/FUA request being sequenced
 * @fq: flush queue
 * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
 * @error: whether an error occurred
 *
 * @rq just completed @seq part of its flush sequence, record the
 * completion and trigger the next step.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
 *
 * RETURNS:
 * %true if requests were added to the dispatch queue, %false otherwise.
 */
static bool blk_flush_complete_seq(struct request *rq,
				   struct blk_flush_queue *fq,
				   unsigned int seq, blk_status_t error)
{
	struct request_queue *q = rq->q;
	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
	bool queued = false, kicked;

	BUG_ON(rq->flush.seq & seq);
	rq->flush.seq |= seq;

	if (likely(!error))
		seq = blk_flush_cur_seq(rq);
	else
		seq = REQ_FSEQ_DONE;

	switch (seq) {
	case REQ_FSEQ_PREFLUSH:
	case REQ_FSEQ_POSTFLUSH:
		/* queue for flush */
		if (list_empty(pending))
			fq->flush_pending_since = jiffies;
		list_move_tail(&rq->flush.list, pending);
		break;

	case REQ_FSEQ_DATA:
		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
		queued = blk_flush_queue_rq(rq, true);
		break;

	case REQ_FSEQ_DONE:
		/*
		 * @rq was previously adjusted by blk_flush_issue() for
		 * flush sequencing and may already have gone through the
		 * flush data request completion path.  Restore @rq for
		 * normal completion and end it.
		 */
		BUG_ON(!list_empty(&rq->queuelist));
		list_del_init(&rq->flush.list);
		blk_flush_restore_request(rq);
		if (q->mq_ops)
			blk_mq_end_request(rq, error);
		else
			__blk_end_request_all(rq, error);
		break;

	default:
		BUG();
	}

	kicked = blk_kick_flush(q, fq);
	return kicked | queued;
}

static void flush_end_io(struct request *flush_rq, blk_status_t error)
{
	struct request_queue *q = flush_rq->q;
	struct list_head *running;
	bool queued = false;
	struct request *rq, *n;
	unsigned long flags = 0;
	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);

	if (q->mq_ops) {
		struct blk_mq_hw_ctx *hctx;

		/* release the tag's ownership to the req cloned from */
		spin_lock_irqsave(&fq->mq_flush_lock, flags);
		hctx = blk_mq_map_queue(q, flush_rq->mq_ctx->cpu);
		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
		flush_rq->tag = -1;
	}

	running = &fq->flush_queue[fq->flush_running_idx];
	BUG_ON(fq->flush_pending_idx == fq->flush_running_idx);

	/* account completion of the flush request */
	fq->flush_running_idx ^= 1;

	if (!q->mq_ops)
		elv_completed_request(q, flush_rq);

	/* and push the waiting requests to the next stage */
	list_for_each_entry_safe(rq, n, running, flush.list) {
		unsigned int seq = blk_flush_cur_seq(rq);

		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
		queued |= blk_flush_complete_seq(rq, fq, seq, error);
	}

	/*
	 * Kick the queue to avoid stall for two cases:
	 * 1. Moving a request silently to empty queue_head may stall the
	 * queue.
	 * 2. When flush request is running in non-queueable queue, the
	 * queue is hold. Restart the queue after flush request is finished
	 * to avoid stall.
	 * This function is called from request completion path and calling
	 * directly into request_fn may confuse the driver.  Always use
	 * kblockd.
	 */
	if (queued || fq->flush_queue_delayed) {
		WARN_ON(q->mq_ops);
		blk_run_queue_async(q);
	}
	fq->flush_queue_delayed = 0;
	if (q->mq_ops)
		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
}

/**
 * blk_kick_flush - consider issuing flush request
 * @q: request_queue being kicked
 * @fq: flush queue
 *
 * Flush related states of @q have changed, consider issuing flush request.
 * Please read the comment at the top of this file for more info.
 *
 * CONTEXT:
 * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
 *
 * RETURNS:
 * %true if flush was issued, %false otherwise.
 */
static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
{
	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
	struct request *first_rq =
		list_first_entry(pending, struct request, flush.list);
	struct request *flush_rq = fq->flush_rq;

	/* C1 described at the top of this file */
	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
		return false;

	/* C2 and C3
	 *
	 * For blk-mq + scheduling, we can risk having all driver tags
	 * assigned to empty flushes, and we deadlock if we are expecting
	 * other requests to make progress. Don't defer for that case.
	 */
	if (!list_empty(&fq->flush_data_in_flight) &&
	    !(q->mq_ops && q->elevator) &&
	    time_before(jiffies,
			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
		return false;

	/*
	 * Issue flush and toggle pending_idx.  This makes pending_idx
	 * different from running_idx, which means flush is in flight.
	 */
	fq->flush_pending_idx ^= 1;

	blk_rq_init(q, flush_rq);

	/*
	 * Borrow tag from the first request since they can't
	 * be in flight at the same time. And acquire the tag's
	 * ownership for flush req.
	 */
	if (q->mq_ops) {
		struct blk_mq_hw_ctx *hctx;

		flush_rq->mq_ctx = first_rq->mq_ctx;
		flush_rq->tag = first_rq->tag;
		fq->orig_rq = first_rq;

		hctx = blk_mq_map_queue(q, first_rq->mq_ctx->cpu);
		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
	}

	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
	flush_rq->rq_disk = first_rq->rq_disk;
	flush_rq->end_io = flush_end_io;

	return blk_flush_queue_rq(flush_rq, false);
}

static void flush_data_end_io(struct request *rq, blk_status_t error)
{
	struct request_queue *q = rq->q;
	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);

	lockdep_assert_held(q->queue_lock);

	/*
	 * Updating q->in_flight[] here for making this tag usable
	 * early. Because in blk_queue_start_tag(),
	 * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and
	 * reserve tags for sync I/O.
	 *
	 * More importantly this way can avoid the following I/O
	 * deadlock:
	 *
	 * - suppose there are 40 fua requests comming to flush queue
	 *   and queue depth is 31
	 * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc
	 *   tag for async I/O any more
	 * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT
	 *   and flush_data_end_io() is called
	 * - the other rqs still can't go ahead if not updating
	 *   q->in_flight[BLK_RW_ASYNC] here, meantime these rqs
	 *   are held in flush data queue and make no progress of
	 *   handling post flush rq
	 * - only after the post flush rq is handled, all these rqs
	 *   can be completed
	 */

	elv_completed_request(q, rq);

	/* for avoiding double accounting */
	rq->rq_flags &= ~RQF_STARTED;

	/*
	 * After populating an empty queue, kick it to avoid stall.  Read
	 * the comment in flush_end_io().
	 */
	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
		blk_run_queue_async(q);
}

static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
{
	struct request_queue *q = rq->q;
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx = rq->mq_ctx;
	unsigned long flags;
	struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);

	hctx = blk_mq_map_queue(q, ctx->cpu);

	/*
	 * After populating an empty queue, kick it to avoid stall.  Read
	 * the comment in flush_end_io().
	 */
	spin_lock_irqsave(&fq->mq_flush_lock, flags);
	blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);

	blk_mq_run_hw_queue(hctx, true);
}

/**
 * blk_insert_flush - insert a new PREFLUSH/FUA request
 * @rq: request to insert
 *
 * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions.
 * or __blk_mq_run_hw_queue() to dispatch request.
 * @rq is being submitted.  Analyze what needs to be done and put it on the
 * right queue.
 */
void blk_insert_flush(struct request *rq)
{
	struct request_queue *q = rq->q;
	unsigned long fflags = q->queue_flags;	/* may change, cache */
	unsigned int policy = blk_flush_policy(fflags, rq);
	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);

	if (!q->mq_ops)
		lockdep_assert_held(q->queue_lock);

	/*
	 * @policy now records what operations need to be done.  Adjust
	 * REQ_PREFLUSH and FUA for the driver.
	 */
	rq->cmd_flags &= ~REQ_PREFLUSH;
	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
		rq->cmd_flags &= ~REQ_FUA;

	/*
	 * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any
	 * of those flags, we have to set REQ_SYNC to avoid skewing
	 * the request accounting.
	 */
	rq->cmd_flags |= REQ_SYNC;

	/*
	 * An empty flush handed down from a stacking driver may
	 * translate into nothing if the underlying device does not
	 * advertise a write-back cache.  In this case, simply
	 * complete the request.
	 */
	if (!policy) {
		if (q->mq_ops)
			blk_mq_end_request(rq, 0);
		else
			__blk_end_request(rq, 0, 0);
		return;
	}

	BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */

	/*
	 * If there's data but flush is not necessary, the request can be
	 * processed directly without going through flush machinery.  Queue
	 * for normal execution.
	 */
	if ((policy & REQ_FSEQ_DATA) &&
	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
		if (q->mq_ops)
			blk_mq_sched_insert_request(rq, false, true, false, false);
		else
			list_add_tail(&rq->queuelist, &q->queue_head);
		return;
	}

	/*
	 * @rq should go through flush machinery.  Mark it part of flush
	 * sequence and submit for further processing.
	 */
	memset(&rq->flush, 0, sizeof(rq->flush));
	INIT_LIST_HEAD(&rq->flush.list);
	rq->rq_flags |= RQF_FLUSH_SEQ;
	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
	if (q->mq_ops) {
		rq->end_io = mq_flush_data_end_io;

		spin_lock_irq(&fq->mq_flush_lock);
		blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
		spin_unlock_irq(&fq->mq_flush_lock);
		return;
	}
	rq->end_io = flush_data_end_io;

	blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
}

/**
 * blkdev_issue_flush - queue a flush
 * @bdev:	blockdev to issue flush for
 * @gfp_mask:	memory allocation flags (for bio_alloc)
 * @error_sector:	error sector
 *
 * Description:
 *    Issue a flush for the block device in question. Caller can supply
 *    room for storing the error offset in case of a flush error, if they
 *    wish to.
 */
int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
		sector_t *error_sector)
{
	struct request_queue *q;
	struct bio *bio;
	int ret = 0;

	if (bdev->bd_disk == NULL)
		return -ENXIO;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;

	/*
	 * some block devices may not have their queue correctly set up here
	 * (e.g. loop device without a backing file) and so issuing a flush
	 * here will panic. Ensure there is a request function before issuing
	 * the flush.
	 */
	if (!q->make_request_fn)
		return -ENXIO;

	bio = bio_alloc(gfp_mask, 0);
	bio_set_dev(bio, bdev);
	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;

	ret = submit_bio_wait(bio);

	/*
	 * The driver must store the error location in ->bi_sector, if
	 * it supports it. For non-stacked drivers, this should be
	 * copied from blk_rq_pos(rq).
	 */
	if (error_sector)
		*error_sector = bio->bi_iter.bi_sector;

	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL(blkdev_issue_flush);

struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
		int node, int cmd_size)
{
	struct blk_flush_queue *fq;
	int rq_sz = sizeof(struct request);

	fq = kzalloc_node(sizeof(*fq), GFP_KERNEL, node);
	if (!fq)
		goto fail;

	if (q->mq_ops)
		spin_lock_init(&fq->mq_flush_lock);

	rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
	if (!fq->flush_rq)
		goto fail_rq;

	INIT_LIST_HEAD(&fq->flush_queue[0]);
	INIT_LIST_HEAD(&fq->flush_queue[1]);
	INIT_LIST_HEAD(&fq->flush_data_in_flight);

	return fq;

 fail_rq:
	kfree(fq);
 fail:
	return NULL;
}

void blk_free_flush_queue(struct blk_flush_queue *fq)
{
	/* bio based request queue hasn't flush queue */
	if (!fq)
		return;

	kfree(fq->flush_rq);
	kfree(fq);
}