cregit-Linux how code gets into the kernel

Release 4.7 block/blk-flush.c

Directory: block
/*
 * Functions to sequence FLUSH 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_{FLUSH|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_FLUSH makes sense, which
 * indicates a simple flush request.  If there is data, REQ_FLUSH 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, FLUSH 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_FLUSH 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_FLUSH 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
 * 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 FLUSH/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 FLUSH) requests.
 *
 * For devices which support FUA, it isn't clear whether C2 (and thus C3)
 * is beneficial.
 *
 * Note that a sequenced FLUSH/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 REQ_FLUSH_SEQ in
 * req_bio_endio().
 *
 * The above peculiarity requires that each FLUSH/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"

/* FLUSH/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_FLUSH) policy |= REQ_FSEQ_PREFLUSH; if (!(fflags & (1UL << QUEUE_FLAG_FUA)) && (rq->cmd_flags & REQ_FUA)) policy |= REQ_FSEQ_POSTFLUSH; } return policy; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo5261.18%125.00%
jens axboejens axboe2225.88%250.00%
jeff moyerjeff moyer1112.94%125.00%
Total85100.00%4100.00%


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

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1562.50%150.00%
jens axboejens axboe937.50%150.00%
Total24100.00%2100.00%


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->cmd_flags &= ~REQ_FLUSH_SEQ; rq->end_io = rq->flush.saved_end_io; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2976.32%240.00%
jeff moyerjeff moyer513.16%120.00%
jens axboejens axboe410.53%240.00%
Total38100.00%5100.00%


static bool blk_flush_queue_rq(struct request *rq, bool add_front) { if (rq->q->mq_ops) { struct request_queue *q = rq->q; blk_mq_add_to_requeue_list(rq, add_front); blk_mq_kick_requeue_list(q); 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; } }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig4955.06%240.00%
mike snitzermike snitzer2325.84%120.00%
jens axboejens axboe1617.98%120.00%
tejun heotejun heo11.12%120.00%
Total89100.00%5100.00%

/** * blk_flush_complete_seq - complete flush sequence * @rq: FLUSH/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, int 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; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo15366.23%436.36%
jens axboejens axboe6126.41%218.18%
ming leiming lei114.76%218.18%
christoph hellwigchristoph hellwig41.73%218.18%
mike snitzermike snitzer20.87%19.09%
Total231100.00%11100.00%


static void flush_end_io(struct request *flush_rq, int 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 = q->mq_ops->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); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe10340.08%218.18%
tejun heotejun heo7228.02%19.09%
ming leiming lei6123.74%436.36%
li shaohuali shaohua93.50%19.09%
shaohua lishaohua li62.33%19.09%
christoph hellwigchristoph hellwig31.17%19.09%
lei minglei ming31.17%19.09%
Total257100.00%11100.00%

/** * 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 */ if (!list_empty(&fq->flush_data_in_flight) && 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 = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu); blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq); } flush_rq->cmd_type = REQ_TYPE_FS; flush_rq->cmd_flags = WRITE_FLUSH | REQ_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); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9242.59%531.25%
ming leiming lei7836.11%531.25%
jens axboejens axboe2210.19%212.50%
christoph hellwigchristoph hellwig2210.19%318.75%
mike snitzermike snitzer20.93%16.25%
Total216100.00%16100.00%


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

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo3361.11%337.50%
ming leiming lei1425.93%225.00%
christoph hellwigchristoph hellwig611.11%225.00%
jens axboejens axboe11.85%112.50%
Total54100.00%8100.00%


static void mq_flush_data_end_io(struct request *rq, int 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 = q->mq_ops->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); if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error)) blk_mq_run_hw_queue(hctx, true); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe8981.65%125.00%
ming leiming lei2018.35%375.00%
Total109100.00%4100.00%

/** * blk_insert_flush - insert a new FLUSH/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. * * CONTEXT: * spin_lock_irq(q->queue_lock) in !mq case */
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); /* * @policy now records what operations need to be done. Adjust * REQ_FLUSH and FUA for the driver. */ rq->cmd_flags &= ~REQ_FLUSH; if (!(fflags & (1UL << QUEUE_FLAG_FUA))) rq->cmd_flags &= ~REQ_FUA; /* * 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_bidi_request(rq, 0, 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_insert_request(rq, false, false, true); } 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->cmd_flags |= REQ_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); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12341.98%422.22%
jens axboejens axboe9733.11%422.22%
jeff moyerjeff moyer4314.68%211.11%
ming leiming lei206.83%316.67%
christoph hellwigchristoph hellwig82.73%422.22%
jan karajan kara20.68%15.56%
Total293100.00%18100.00%

/** * 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. If WAIT flag is not passed then caller may check only what * request was pushed in some internal queue for later handling. */
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->bi_bdev = bdev; ret = submit_bio_wait(WRITE_FLUSH, 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; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe9076.27%112.50%
dave chinnerdave chinner119.32%112.50%
dmitriy monakhovdmitriy monakhov108.47%225.00%
kent overstreetkent overstreet43.39%225.00%
tejun heotejun heo21.69%112.50%
christoph hellwigchristoph hellwig10.85%112.50%
Total118100.00%8100.00%

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; }

Contributors

PersonTokensPropCommitsCommitProp
ming leiming lei13790.73%480.00%
jens axboejens axboe149.27%120.00%
Total151100.00%5100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
ming leiming lei29100.00%2100.00%
Total29100.00%2100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo63935.50%1225.53%
jens axboejens axboe55530.83%48.51%
ming leiming lei38121.17%919.15%
christoph hellwigchristoph hellwig945.22%919.15%
jeff moyerjeff moyer593.28%36.38%
mike snitzermike snitzer271.50%12.13%
dave chinnerdave chinner110.61%12.13%
dmitriy monakhovdmitriy monakhov100.56%24.26%
li shaohuali shaohua90.50%12.13%
shaohua lishaohua li60.33%12.13%
kent overstreetkent overstreet40.22%24.26%
lei minglei ming30.17%12.13%
jan karajan kara20.11%12.13%
Total1800100.00%47100.00%
Directory: block
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
{% endraw %}