/*
* 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
* q->flush_queue[q->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"
/* 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);
static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
{
unsigned int policy = 0;
if (blk_rq_sectors(rq))
policy |= REQ_FSEQ_DATA;
if (fflags & REQ_FLUSH) {
if (rq->cmd_flags & REQ_FLUSH)
policy |= REQ_FSEQ_PREFLUSH;
if (!(fflags & REQ_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->cmd_flags &= ~REQ_FLUSH_SEQ;
rq->end_io = rq->flush.saved_end_io;
blk_clear_rq_complete(rq);
}
static void mq_flush_data_run(struct work_struct *work)
{
struct request *rq;
rq = container_of(work, struct request, mq_flush_data);
memset(&rq->csd, 0, sizeof(rq->csd));
blk_mq_run_request(rq, true, false);
}
static void blk_mq_flush_data_insert(struct request *rq)
{
INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
kblockd_schedule_work(rq->q, &rq->mq_flush_data);
}
/**
* blk_flush_complete_seq - complete flush sequence
* @rq: FLUSH/FUA request being sequenced
* @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 q->mq_flush_lock)
*
* RETURNS:
* %true if requests were added to the dispatch queue, %false otherwise.
*/
static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
int error)
{
struct request_queue *q = rq->q;
struct list_head *pending = &q->flush_queue[q->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))
q->flush_pending_since = jiffies;
list_move_tail(&rq->flush.list, pending);
break;
case REQ_FSEQ_DATA:
list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
if (q->mq_ops)
blk_mq_flush_data_insert(rq);
else {
list_add(&rq->queuelist, &q->queue_head);
queued = 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_io(rq, error);
else
__blk_end_request_all(rq, error);
break;
default:
BUG();
}
kicked = blk_kick_flush(q);
/* blk_mq_run_flush will run queue */
if (q->mq_ops)
return queued;
return kicked | queued;
}
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;
if (q->mq_ops) {
blk_mq_free_request(flush_rq);
spin_lock_irqsave(&q->mq_flush_lock, flags);
}
running = &q->flush_queue[q->flush_running_idx];
BUG_ON(q->flush_pending_idx == q->flush_running_idx);
/* account completion of the flush request */
q->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, 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